Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ThinkingCap-Qwen3.6-27B-ROCmFP4-STRIX-embF16-headQ6.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-F32.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,269 @@
+---
+base_model: bottlecapai/ThinkingCap-Qwen3.6-27B
+license: apache-2.0
+library_name: gguf
+tags:
+- gguf
+- rocmfp4
+- qwen3.6
+- mtp
+- speculative-decoding
+- efficient-thinking
+- strix-halo
+- amd
+- rocm
+- vulkan
+base_model_relation: quantized
+---
+
+<div style="border:2px solid currentColor; font-family:ui-monospace,'SF Mono','Cascadia Mono',Consolas,'Liberation Mono',monospace;">
+  <div style="border-bottom:1px solid currentColor; padding:6px 12px; font-size:11px; letter-spacing:3px; text-transform:uppercase; opacity:0.7; text-align:center;">PLUNDERSTRUCK // ROCmFP4 QUANTIZED MODEL // STRIX HALO · gfx1151</div>
+  <div style="padding:14px; display:flex; flex-wrap:wrap; align-items:center; justify-content:center; gap:18px;">
+<pre style="margin:0; flex:0 0 auto; font-family:ui-monospace,'SF Mono','Cascadia Mono',Consolas,monospace; font-size:6px; line-height:1.1; letter-spacing:0;">
+        ▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
+      ▟███████████████████████▙
+   ▄▟█████████████████████████████▙▄
+ ▟███████████████████████████████████▙
+▐███████████████▛▀▀▀▀▀▜███████████████▌
+▝████████████████       ████████████▛▘
+       ▐████▛▘             ▝▜████▌
+         ▐█▌       ▟▙        ▐█▌
+         ▐█▌      ▟███▙       ▐█▌
+          ▀▀     ▟█████▙      ▀▀
+                ▟███████▙
+</pre>
+    <div style="flex:0 1 auto; max-width:100%; text-align:center;">
+      <div style="font-size:23px; font-weight:800; letter-spacing:1px;">THINKINGCAP-QWEN3.6-27B-MTP</div>
+      <div style="font-size:12.5px; letter-spacing:1px; opacity:0.8; margin-top:5px;"><span style="white-space:nowrap;">4-BIT ROCmFP4</span> · <span style="white-space:nowrap;">EFFICIENT-THINKING</span> · <span style="white-space:nowrap;">MTP SELF-SPECULATIVE DECODE</span> · <span style="white-space:nowrap;">VISION-CAPABLE</span> · <span style="white-space:nowrap;">SINGLE AMD APU</span></div>
+    </div>
+  </div>
+  <table style="display:table; table-layout:fixed; width:100%; margin:0; border-collapse:collapse; border-radius:0; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12px;">
+    <tr>
+      <td style="border-top:1px solid currentColor; border-right:1px solid currentColor; padding:8px 12px;"><div style="font-size:10px; letter-spacing:1px; opacity:0.6;">FORMAT</div><div style="font-weight:700;">ROCmFP4 4-BIT</div></td>
+      <td style="border-top:1px solid currentColor; border-right:1px solid currentColor; padding:8px 12px;"><div style="font-size:10px; letter-spacing:1px; opacity:0.6;">PRECISION</div><div style="font-weight:700;">4.94 BPW</div></td>
+      <td style="border-top:1px solid currentColor; border-right:1px solid currentColor; padding:8px 12px;"><div style="font-size:10px; letter-spacing:1px; opacity:0.6;">SIZE</div><div style="font-weight:700;">16.9 GB</div></td>
+      <td style="border-top:1px solid currentColor; padding:8px 12px;"><div style="font-size:10px; letter-spacing:1px; opacity:0.6;">CONTEXT</div><div style="font-weight:700;">262 K</div></td>
+    </tr>
+    <tr>
+      <td style="border-top:1px solid currentColor; border-right:1px solid currentColor; padding:8px 12px;"><div style="font-size:10px; letter-spacing:1px; opacity:0.6;">DRAFT</div><div style="font-weight:700;">MTP n-max 5</div></td>
+      <td style="border-top:1px solid currentColor; border-right:1px solid currentColor; padding:8px 12px;"><div style="font-size:10px; letter-spacing:1px; opacity:0.6;">VISION</div><div style="font-weight:700;">QWEN3-VL</div></td>
+      <td style="border-top:1px solid currentColor; border-right:1px solid currentColor; padding:8px 12px;"><div style="font-size:10px; letter-spacing:1px; opacity:0.6;">BACKEND</div><div style="font-weight:700;">VULKAN0</div></td>
+      <td style="border-top:1px solid currentColor; padding:8px 12px;"><div style="font-size:10px; letter-spacing:1px; opacity:0.6;">CALIBRATION</div><div style="font-weight:700;">non-imatrix</div></td>
+    </tr>
+  </table>
+</div>
+
+<div style="border:1px solid currentColor; padding:10px 13px; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12.5px; margin:14px 0;">
+<b>ThinkingCap-Qwen3.6-27B</b> is <a href="https://huggingface.co/bottlecapai">bottlecapai</a>'s efficient-reasoning finetune of <b>Qwen3.6-27B</b> — trained to cut thinking-token consumption roughly in half (<b>↓45.8%</b> macro average) while holding answer quality, across knowledge, math, code, long-context, and agentic tasks. It scores <b>GPQA-Diamond 83.8</b>, <b>MMLU-Pro 85.4</b>, <b>GSM8K 96.5</b> (bottlecapai reported). This repo is the <b>ROCmFP4</b> quantization tuned for a single AMD Strix Halo APU, with the <b>MTP head preserved</b> for self-speculative decode and vision carried through from the base model.
+</div>
+
+<div style="border:2px solid #dc2626; padding:10px 13px; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12.5px; margin:14px 0;">
+<b style="color:#dc2626; letter-spacing:1px;">⚠ REQUIRES THE ROCmFPX FORK</b><br>
+The custom <code>q4_0_rocmfp4</code> / <code>q4_0_rocmfp4_fast</code> tensor types <b>will not load in stock llama.cpp, LM Studio, Ollama, Jan, or koboldcpp</b>. Build/run with <a href="https://github.com/charlie12345/ROCmFPX">charlie12345/ROCmFPX</a> · branch <code>experimental-rocmfpx-branch</code>:
+<br><br>
+<code>git clone https://github.com/charlie12345/ROCmFPX</code><br>
+<code>cd ROCmFPX &amp;&amp; git checkout experimental-rocmfpx-branch</code><br>
+<code>env JOBS=16 scripts/build-strix-rocmfp4-mtp.sh</code>
+</div>
+
+<div style="border:1px solid currentColor; padding:8px 13px; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12px; margin:14px 0; opacity:0.85;">
+<b>NOTE //</b> Ignore HuggingFace's auto-detected "F16" badge — its parser can't read ROCmFP4 and mislabels by the genuinely-f16 token embeddings. This is a <b>~4.9 bpw 4-bit</b> file; pick by filename in <i>Files and versions</i>.
+</div>
+
+<div style="font-family:ui-monospace,'SF Mono',Consolas,monospace; font-weight:800; font-size:14px; letter-spacing:2px; text-transform:uppercase; border-bottom:2px solid currentColor; padding-bottom:5px; margin:26px 0 12px;"><span style="color:#ea580c;">01</span> · FILES</div>
+
+<div style="overflow:hidden; border-radius:0;">
+<table style="width:100%; border-collapse:collapse; border-radius:0; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12.5px;">
+<thead><tr>
+<th style="border:1px solid currentColor; padding:7px 10px; text-align:left; text-transform:uppercase; font-size:10px; letter-spacing:1px;">File</th>
+<th style="border:1px solid currentColor; padding:7px 10px; text-align:left; text-transform:uppercase; font-size:10px; letter-spacing:1px;">Size</th>
+<th style="border:1px solid currentColor; padding:7px 10px; text-align:left; text-transform:uppercase; font-size:10px; letter-spacing:1px;">Output head</th>
+<th style="border:1px solid currentColor; padding:7px 10px; text-align:left; text-transform:uppercase; font-size:10px; letter-spacing:1px;">Pick if</th>
+</tr></thead>
+<tbody>
+<tr><td style="border:1px solid currentColor; padding:7px 10px;"><code>…-STRIX-embF16-headQ6.gguf</code> ★</td><td style="border:1px solid currentColor; padding:7px 10px;">16.9 GB</td><td style="border:1px solid currentColor; padding:7px 10px;">Q6_K</td><td style="border:1px solid currentColor; padding:7px 10px;"><b>the one build</b> — best speed/quality balance: f16 embeddings + Q6 output head on the fast single-scale body</td></tr>
+</tbody>
+</table>
+</div>
+
+One file — the **best speed/quality balance** in ROCmFP4 for Strix Halo. It keeps the two quality levers that are actually *felt* — genuine **f16 token embeddings** (from F16 source) and a **Q6_K output head** — on the fast single-scale `q4_0_rocmfp4_fast` body, plus the **MTP head**, with **no imatrix** (this recipe's daily-driver default; see §05). Repo bundles the **[`mmproj-F32.gguf`](./mmproj-F32.gguf)** Qwen3-VL vision projector and **[`chat_template.jinja`](./chat_template.jinja)** (froggeric's unified Qwen3.6 template — tool calls + inline think-toggle + vision).
+
+<div style="overflow:hidden; border-radius:0;">
+<table style="width:100%; border-collapse:collapse; border-radius:0; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12.5px;">
+<tbody>
+<tr><td style="border:1px solid currentColor; padding:8px 11px; width:42%;">token_embd</td><td style="border:1px solid currentColor; padding:8px 11px; font-weight:700;">F16 (full precision — a lookup, ~zero decode cost)</td></tr>
+<tr><td style="border:1px solid currentColor; padding:8px 11px;">attention K/V (+ fused QKV)</td><td style="border:1px solid currentColor; padding:8px 11px; font-weight:700;"><code>q4_0_rocmfp4</code> (dual-scale)</td></tr>
+<tr><td style="border:1px solid currentColor; padding:8px 11px;">FFN, lm-head, rest</td><td style="border:1px solid currentColor; padding:8px 11px; font-weight:700;"><code>q4_0_rocmfp4_fast</code> (single-scale)</td></tr>
+<tr><td style="border:1px solid currentColor; padding:8px 11px;">MTP head</td><td style="border:1px solid currentColor; padding:8px 11px; font-weight:700;">preserved (<code>nextn_predict_layers=1</code>)</td></tr>
+</tbody>
+</table>
+</div>
+
+<div style="font-family:ui-monospace,'SF Mono',Consolas,monospace; font-weight:800; font-size:14px; letter-spacing:2px; text-transform:uppercase; border-bottom:2px solid currentColor; padding-bottom:5px; margin:26px 0 12px;"><span style="color:#ea580c;">02</span> · QUICK START</div>
+
+Run from the folder holding the `.gguf` + `chat_template.jinja`:
+
+```bash
+env HSA_OVERRIDE_GFX_VERSION=11.5.1 GGML_HIP_ENABLE_UNIFIED_MEMORY=1 \
+llama-server \
+  -m ThinkingCap-Qwen3.6-27B-ROCmFP4-STRIX-embF16-headQ6.gguf \
+  --alias thinkingcap-27b \
+  --host 0.0.0.0 \
+  --port 8080 \
+  -dev Vulkan0 \
+  -ngl 999 \
+  -fa on \
+  -c 262144 \
+  -b 2048 \
+  -ub 256 \
+  -t 16 \
+  -tb 16 \
+  -ctk f16 \
+  -ctv f16 \
+  -cpent 256 \
+  -ctxcp 32 \
+  --cache-reuse 256 \
+  --cache-ram 65536 \
+  --temp 0.6 \
+  --top-p 0.95 \
+  --top-k 20 \
+  --min-p 0.0 \
+  --spec-type draft-mtp \
+  --spec-draft-device Vulkan0 \
+  --spec-draft-ngl all \
+  --spec-draft-type-k f16 \
+  --spec-draft-type-v f16 \
+  --spec-draft-n-max 5 \
+  --spec-draft-n-min 2 \
+  --spec-draft-p-min 0.0 \
+  --spec-draft-p-split 0.10 \
+  --chat-template-file chat_template.jinja \
+  --reasoning on \
+  --reasoning-format deepseek \
+  --chat-template-kwargs '{"preserve_thinking": true}' \
+  --jinja \
+  --parallel 1 \
+  --metrics \
+  --no-mmap \
+  --mmproj mmproj-F32.gguf \
+  --image-min-tokens 1024
+```
+
+The **last two lines enable vision** — the `mmproj-F32.gguf` Qwen3-VL projector is **bundled in this repo**; omit them for text-only. **`--image-min-tokens 1024` is required whenever `--mmproj` is set.**
+
+<div style="border:1px solid currentColor; padding:8px 13px; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12px; margin:12px 0; opacity:0.85;">
+<b>NOTE //</b> bottlecapai's own recommended sampling for general use is <code>temp=1.0, top_p=0.95, top_k=20, min_p=0.0</code>. We serve at <code>temp 0.6</code> (Qwen3.6 "precise coding" preset) by default — raise to <code>1.0</code> for open-ended/creative tasks.
+</div>
+
+<div style="overflow:hidden; border-radius:0;">
+<table style="width:100%; border-collapse:collapse; border-radius:0; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12px;">
+<thead><tr>
+<th style="border:1px solid currentColor; padding:6px 10px; text-align:left; text-transform:uppercase; font-size:10px; letter-spacing:1px; width:40%;">Flag</th>
+<th style="border:1px solid currentColor; padding:6px 10px; text-align:left; text-transform:uppercase; font-size:10px; letter-spacing:1px;">Function</th>
+</tr></thead>
+<tbody>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>HSA_OVERRIDE_GFX_VERSION=11.5.1</code></td><td style="border:1px solid currentColor; padding:6px 10px;">treat the APU as gfx1151 (Strix Halo)</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>GGML_HIP_ENABLE_UNIFIED_MEMORY=1</code></td><td style="border:1px solid currentColor; padding:6px 10px;">allow use of the full 128 GB unified memory</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>-dev Vulkan0</code></td><td style="border:1px solid currentColor; padding:6px 10px;">run on Vulkan (KHR_coopmat) — beats ROCm/HIP here for ROCmFP4 on Strix Halo</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>-ngl 999 · -fa on</code></td><td style="border:1px solid currentColor; padding:6px 10px;">offload all layers · flash attention</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>-c 262144</code></td><td style="border:1px solid currentColor; padding:6px 10px;">context length (256K)</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>-b 2048 · -ub 256 · -t/-tb 16</code></td><td style="border:1px solid currentColor; padding:6px 10px;">prefill batch / micro-batch (256 = prefill optimum) · CPU threads</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>-ctk f16 · -ctv f16</code></td><td style="border:1px solid currentColor; padding:6px 10px;">f16 KV cache — how we run it; drop to <code>q8_0</code>/<code>q4_0</code> to use less memory</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>-cpent · -ctxcp · --cache-reuse · --cache-ram 65536</code></td><td style="border:1px solid currentColor; padding:6px 10px;">cross-turn KV checkpointing + 64 GB resident reuse cache</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>--temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.0</code></td><td style="border:1px solid currentColor; padding:6px 10px;">precise-coding sampling (bottlecapai recommends 1.0 for general use)</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>--spec-type draft-mtp · --spec-draft-n-max 5 · n-min 2</code></td><td style="border:1px solid currentColor; padding:6px 10px;">built-in MTP head, self-speculative; draft depth up to 5, at least 2</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>--spec-draft-device Vulkan0 · -ngl all · type-k/v f16</code></td><td style="border:1px solid currentColor; padding:6px 10px;">draft head on Vulkan, fully offloaded, f16 draft KV</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>--chat-template-file chat_template.jinja</code></td><td style="border:1px solid currentColor; padding:6px 10px;">bundled froggeric template (tool calls + think-toggle + vision)</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>--reasoning on --reasoning-format deepseek + kwargs {preserve_thinking:true}</code></td><td style="border:1px solid currentColor; padding:6px 10px;">clean <code>content</code>+<code>reasoning_content</code>; keep <code>&lt;think&gt;</code> across turns so cross-turn cache survives</td></tr>
+<tr><td style="border:1px solid currentColor; padding:6px 10px;"><code>--jinja --parallel 1 --metrics --no-mmap</code></td><td style="border:1px solid currentColor; padding:6px 10px;">apply template · single slot · metrics · weights in RAM</td></tr>
+</tbody>
+</table>
+</div>
+
+**OpenAI-compatible client (e.g. OpenCode).** In single-model mode llama-server ignores the request's `model` field, so the client's model name is just a label.
+
+- Base URL: `http://<host>:8080/v1` · API key: any non-empty string (e.g. `sk-local`)
+- Model id this server reports: `thinkingcap-27b`
+
+A patched OpenCode that compacts conversation history **without** invalidating the prompt cache is at [`PlunderStruck/opencode`](https://github.com/PlunderStruck/opencode) — pair it with the checkpoint flags to keep long sessions fast.
+
+<div style="font-family:ui-monospace,'SF Mono',Consolas,monospace; font-weight:800; font-size:14px; letter-spacing:2px; text-transform:uppercase; border-bottom:2px solid currentColor; padding-bottom:5px; margin:26px 0 12px;"><span style="color:#ea580c;">03</span> · VISION</div>
+
+Qwen3-VL lineage — vision works via the **bundled `mmproj-F32.gguf`** projector at launch with `--mmproj` (no different LLM GGUF needed).
+
+```bash
+# add to your llama-server launch:
+  --mmproj mmproj-F32.gguf \
+  --image-min-tokens 1024     # REQUIRED — Qwen-VL needs >=1024 image tokens or it misreads fine detail
+```
+
+<div style="border:1px solid currentColor; padding:8px 13px; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12px; margin:12px 0; opacity:0.85;">
+<b>NOTE //</b> this is a thinking model — for one-shot image Q&amp;A, use the bundled template's think-toggle or allow enough tokens to finish <code>&lt;think&gt;</code>, else the visible answer can come back empty. With <code>--mmproj</code> loaded the server disables the <code>--cache-reuse</code> feature (multimodal caching isn't supported).
+</div>
+
+<div style="font-family:ui-monospace,'SF Mono',Consolas,monospace; font-weight:800; font-size:14px; letter-spacing:2px; text-transform:uppercase; border-bottom:2px solid currentColor; padding-bottom:5px; margin:26px 0 12px;"><span style="color:#ea580c;">04</span> · PERFORMANCE &amp; QUALITY</div>
+
+**This is the best speed/quality balance in ROCmFP4 — by design, not the absolute fastest.** It keeps the two quality levers that are actually *felt* — genuine **f16 token embeddings** and a **Q6_K output head** — on the fast single-scale body, with **no imatrix** calibration (this recipe's default for the dense Qwen3.6-27B line — see the [27B card](https://huggingface.co/plunderstruck/Qwen3.6-27B-MTP-ROCmFP4-GGUF) for the full lever sweep and rationale).
+
+<div style="border:1px solid currentColor; padding:8px 13px; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12px; margin:12px 0; opacity:0.9;">
+<b>WANT MAXIMUM FIDELITY INSTEAD OF SPEED?</b> bottlecapai's own GGUF repo ships standard K-quants — <a href="https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.6-27B-GGUF"><b>Q4_K_M / Q8_0</b></a> — more faithful to the source at a slower decode. We optimize for throughput in ROCmFP4 on Strix Halo; grab one of those for the last bit of fidelity.
+</div>
+
+Hands-on, on a Framework Desktop / AMD Ryzen AI Max+ 395 (gfx1151, 128 GB unified):
+
+<div style="overflow:hidden; border-radius:0;">
+<table style="width:100%; border-collapse:collapse; border-radius:0; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12.5px;">
+<tbody>
+<tr><td style="border:1px solid currentColor; padding:8px 11px; width:42%;">DECODE</td><td style="border:1px solid currentColor; padding:8px 11px; font-weight:700;">~30 t/s (Vulkan / Strix Halo, thinking on)</td></tr>
+<tr><td style="border:1px solid currentColor; padding:8px 11px;">MTP DRAFT ACCEPTANCE</td><td style="border:1px solid currentColor; padding:8px 11px; font-weight:700;">~4.15 mean accepted length (n-max 5 / n-min 2)</td></tr>
+<tr><td style="border:1px solid currentColor; padding:8px 11px;">CONTEXT @ LOAD</td><td style="border:1px solid currentColor; padding:8px 11px;">full 262144, f16 KV</td></tr>
+<tr><td style="border:1px solid currentColor; padding:8px 11px;">QUANTIZATION</td><td style="border:1px solid currentColor; padding:8px 11px;">non-imatrix</td></tr>
+</tbody>
+</table>
+</div>
+
+<div style="border:1px solid currentColor; padding:8px 13px; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12px; margin:12px 0; opacity:0.85;">
+<b>NOTE //</b> built on a fork snapshot carrying an upstream fix for a self-speculative-decode bug affecting M-RoPE architectures (Qwen3.6 included) — MTP was silently degrading to plain decode under certain batch shapes on some builds. This quant's measured acceptance (~4.15) reflects the fixed path; older ROCmFPX builds may show materially lower MTP throughput on this model family.
+</div>
+
+<div style="font-family:ui-monospace,'SF Mono',Consolas,monospace; font-weight:800; font-size:14px; letter-spacing:2px; text-transform:uppercase; border-bottom:2px solid currentColor; padding-bottom:5px; margin:26px 0 12px;"><span style="color:#ea580c;">05</span> · BUILD (REPRODUCIBLE)</div>
+
+Build the fork:
+
+```bash
+git clone https://github.com/charlie12345/ROCmFPX
+cd ROCmFPX && git checkout experimental-rocmfpx-branch
+env JOBS=16 scripts/build-strix-rocmfp4-mtp.sh
+```
+
+Quantize from the bottlecapai F16 GGUF — ROCmFP4 body, genuine f16 embeddings, Q6_K head, no imatrix:
+
+```bash
+# the one build: STRIX preset + f16 embeddings + Q6_K output head
+llama-quantize \
+  --token-embedding-type f16 \
+  --output-tensor-type q6_K \
+  ThinkingCap-Qwen3.6-27B-f16.gguf \
+  ThinkingCap-Qwen3.6-27B-ROCmFP4-STRIX-embF16-headQ6.gguf \
+  Q4_0_ROCMFP4_STRIX
+```
+
+**Architecture (`qwen35`):** 64 blocks, 5120 hidden, dense (not MoE), **`nextn_predict_layers=1`** MTP head — self-speculative **draft-MTP** survives quantization. **Format:** ROCmFP4 is a 4-bit weight format for AMD using an FP4-derived value codebook plus one (FAST) or two (dual) UE4M3/FP8 scale bytes per 32-weight block; tensor-aware. **This build** (`STRIX-embF16-headQ6`): quality-biased STRIX preset + f16 token embeddings (full precision; a lookup, so ~zero decode cost) + a Q6_K output head. Attention K/V (+ fused QKV) run `q4_0_rocmfp4` (dual-scale); FFN/rest run `q4_0_rocmfp4_fast` (single-scale).
+
+> Experimental research build for AMD Strix Halo — hardware-, driver-, model-, and prompt-sensitive, may not reproduce on other GPUs. **Not** native FP4 tensor-core execution. Do not treat these numbers as upstream llama.cpp claims.
+
+<div style="font-family:ui-monospace,'SF Mono',Consolas,monospace; font-weight:800; font-size:14px; letter-spacing:2px; text-transform:uppercase; border-bottom:2px solid currentColor; padding-bottom:5px; margin:26px 0 12px;"><span style="color:#ea580c;">06</span> · LINEAGE &amp; CREDITS</div>
+
+<div style="overflow:hidden; border-radius:0;">
+<table style="width:100%; border-collapse:collapse; border-radius:0; font-family:ui-monospace,'SF Mono',Consolas,monospace; font-size:12.5px;">
+<tbody>
+<tr><td style="border:1px solid currentColor; padding:8px 11px; width:26%;">BASE MODEL</td><td style="border:1px solid currentColor; padding:8px 11px;"><a href="https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.6-27B">bottlecapai/ThinkingCap-Qwen3.6-27B</a> — efficient-thinking finetune of <a href="https://huggingface.co/Qwen/Qwen3.6-27B">Qwen/Qwen3.6-27B</a> (Apache 2.0). This is a derivative quantization that inherits the Apache 2.0 license.</td></tr>
+<tr><td style="border:1px solid currentColor; padding:8px 11px;">F16 GGUF SOURCE</td><td style="border:1px solid currentColor; padding:8px 11px;"><a href="https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.6-27B-GGUF">bottlecapai/ThinkingCap-Qwen3.6-27B-GGUF</a> · <code>ThinkingCap-Qwen3.6-27B-f16.gguf</code></td></tr>
+<tr><td style="border:1px solid currentColor; padding:8px 11px;">FORMAT + RUNTIME</td><td style="border:1px solid currentColor; padding:8px 11px;"><a href="https://github.com/charlie12345/ROCmFPX">charlie12345/ROCmFPX</a> (based on llama.cpp, MIT)</td></tr>
+<tr><td style="border:1px solid currentColor; padding:8px 11px;">CHAT TEMPLATE</td><td style="border:1px solid currentColor; padding:8px 11px;"><a href="https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates">froggeric/Qwen-Fixed-Chat-Templates</a></td></tr>
+<tr><td style="border:1px solid currentColor; padding:8px 11px;">BENCHMARKS (BASE)</td><td style="border:1px solid currentColor; padding:8px 11px;">GPQA-Diamond 83.8±1.9 · MMLU-Pro 85.4±0.2 · GSM8K 96.5±0.3 · thinking-token reduction ↓45.8% macro avg (bottlecapai reported)</td></tr>
+</tbody>
+</table>
+</div>
+
+*Derivative quantization — Apache 2.0, same as the base model.*

ThinkingCap-Qwen3.6-27B-ROCmFP4-STRIX-embF16-headQ6.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac375e5bb2161e6b49b41e4a2edddcc5c99a5390331f9dd421061100c6900a09
+size 16881328096

chat_template.jinja

@@ -0,0 +1,287 @@
+{%- set template_version = "qwen3.6-froggeric-v20" %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- set add_vision_id = add_vision_id if add_vision_id is defined else false %}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else true %}
+{%- set auto_disable_thinking_with_tools = auto_disable_thinking_with_tools if auto_disable_thinking_with_tools is defined else false %}
+{%- set _preserve_thinking = preserve_thinking if preserve_thinking is defined else false %}
+{%- set max_tool_arg_chars = max_tool_arg_chars if max_tool_arg_chars is defined else 0 %}
+{%- set max_tool_response_chars = max_tool_response_chars if max_tool_response_chars is defined else 0 %}
+{%- set _has_tools = (tools is defined and tools and tools is iterable and tools is not mapping) %}
+{%- set ns_state = namespace(thinking=enable_thinking) %}
+{%- if auto_disable_thinking_with_tools and _has_tools %}
+    {%- set ns_state.thinking = false %}
+{%- endif %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if item is mapping %}
+                {%- if item.type == 'image' or 'image' in item or 'image_url' in item %}
+                    {%- if is_system_content %}
+                        {{- raise_exception('System message cannot contain images.') }}
+                    {%- endif %}
+                    {%- if do_vision_count %}
+                        {%- set image_count.value = image_count.value + 1 %}
+                    {%- endif %}
+                    {%- if add_vision_id %}
+                        {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                    {%- endif %}
+                    {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+                {%- elif item.type == 'video' or 'video' in item %}
+                    {%- if is_system_content %}
+                        {{- raise_exception('System message cannot contain videos.') }}
+                    {%- endif %}
+                    {%- if do_vision_count %}
+                        {%- set video_count.value = video_count.value + 1 %}
+                    {%- endif %}
+                    {%- if add_vision_id %}
+                        {{- 'Video ' ~ video_count.value ~ ': ' }}
+                    {%- endif %}
+                    {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+                {%- elif 'text' in item %}
+                    {{- item.text }}
+                {%- else %}
+                    {{- raise_exception('Unexpected item type in content.') }}
+                {%- endif %}
+            {%- else %}
+                {{- item | string }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- set _first_role = messages[0].role %}
+{%- if _first_role == 'system' or _first_role == 'developer' %}
+    {%- set _sys_msg = messages[0] %}
+    {%- set _msgs = messages[1:] %}
+{%- else %}
+    {%- set _sys_msg = none %}
+    {%- set _msgs = messages %}
+{%- endif %}
+{%- set _sc = '' %}
+{%- if _sys_msg is not none %}
+    {%- set _sc = render_content(_sys_msg.content, false, true) | trim %}
+    {%- if '<|think_off|>' in _sc %}
+        {%- set ns_state.thinking = false %}
+        {%- set _sc = _sc.split('<|think_off|>') | join('') | trim %}
+    {%- elif '<|think_on|>' in _sc %}
+        {%- set ns_state.thinking = true %}
+        {%- set _sc = _sc.split('<|think_on|>') | join('') | trim %}
+    {%- endif %}
+{%- endif %}
+{%- if _has_tools %}
+    {{- '<|im_start|>system\n' }}
+    {{- '# Tools\n\nYou have access to the following functions:\n\n<tools>' }}
+    {%- for tool in tools %}
+        {{- '\n' }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- '\n</tools>' }}
+    {%- set tool_instructions %}
+If you choose to call a function ONLY reply in the following format with NO suffix:
+
+<think>
+Brief explanation of tool call
+</think>
+<tool_call>
+<function=example_function_name>
+<parameter=example_parameter_1>
+value_1
+</parameter>
+<parameter=example_parameter_2>
+This is the value for the second parameter
+that can span
+multiple lines
+</parameter>
+</function>
+</tool_call>
+
+<IMPORTANT>
+Reminder:
+- You can use the <think></think> block to plan your next tool call OR to synthesize data and formulate your final response to the user.
+- ALL explanation and reasoning MUST be placed strictly inside the <think></think> block.
+- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags.
+- If you choose to call a tool, you MUST output the <tool_call> block IMMEDIATELY after closing </think>. Do NOT output any conversational text before the tool call.
+- The <tool_call> and <function> tags MUST be at the very beginning of a new line, with NO spaces or indentation before them.
+- To call multiple functions, output a separate, completely closed <tool_call></tool_call> block for EACH function. Do NOT nest <tool_call> blocks.
+- If you have gathered all necessary data and do not need to call a tool, answer the question like normal and provide your final response to the user IMMEDIATELY after closing </think>.
+</IMPORTANT>
+    {%- endset %}
+    {{- '\n\n' ~ tool_instructions | trim }}
+    {%- if _sc %}
+        {{- '\n\n' + _sc }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if _sc %}
+        {{- '<|im_start|>system\n' + _sc + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set _last_idx = _msgs | length - 1 %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=_last_idx) %}
+{%- for message in _msgs[::-1] %}
+    {%- set index = (_msgs | length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == 'user' %}
+        {%- set _rc = render_content(message.content, false) | trim %}
+        {%- if not (_rc.startswith('<tool_response>') and _rc.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {%- if _last_idx > 50 %}
+        {%- set ns.last_query_index = _last_idx %}
+    {%- else %}
+        {%- set ns.last_query_index = 0 %}
+    {%- endif %}
+{%- endif %}
+{%- set ns2 = namespace(prev_role='', consecutive_failures=0) %}
+{%- for message in _msgs %}
+    {%- set is_system = (message.role == "system" or message.role == "developer") %}
+    {%- set content = render_content(message.content, true, is_system) | trim %}
+    {%- if '<|think_off|>' in content %}
+        {%- set ns_state.thinking = false %}
+        {%- set content = content.split('<|think_off|>') | join('') | trim %}
+    {%- elif '<|think_on|>' in content %}
+        {%- set ns_state.thinking = true %}
+        {%- set content = content.split('<|think_on|>') | join('') | trim %}
+    {%- endif %}
+    {%- if is_system %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- elif message.role == 'user' %}
+        {%- set ns2.consecutive_failures = 0 %}
+        {{- '<|im_start|>user\n' + content + '<|im_end|>\n' }}
+    {%- elif message.role == 'assistant' %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- if message.reasoning_content is string %}
+                {%- set reasoning_content = message.reasoning_content %}
+            {%- else %}
+                {%- set reasoning_content = message.reasoning_content | string %}
+            {%- endif %}
+        {%- else %}
+            {%- set _think_end = '' %}
+            {%- if '</think>' in content %}
+                {%- set _think_end = '</think>' %}
+            {%- elif '</thinking>' in content %}
+                {%- set _think_end = '</thinking>' %}
+            {%- elif '</ think>' in content %}
+                {%- set _think_end = '</ think>' %}
+            {%- elif '</think >' in content %}
+                {%- set _think_end = '</think >' %}
+            {%- endif %}
+            {%- if _think_end %}
+                {%- if _think_end == '</thinking>' %}
+                    {%- set _think_start = '<thinking>' %}
+                {%- else %}
+                    {%- set _think_start = '<think>' %}
+                {%- endif %}
+                {%- set reasoning_content = content.split(_think_end)[0].rstrip('\n') %}
+                {%- if _think_start in reasoning_content %}
+                    {%- set reasoning_content = reasoning_content.split(_think_start)[-1].lstrip('\n') %}
+                {%- endif %}
+                {%- set content = content.split(_think_end)[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content | trim %}
+        {%- if (_preserve_thinking or loop.index0 > ns.last_query_index) and reasoning_content %}
+            {{- '<|im_start|>assistant\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>assistant\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls is defined and message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined and tool_call.function is not none %}
+                    {%- set tc = tool_call.function %}
+                {%- else %}
+                    {%- set tc = tool_call %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content | trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tc.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tc.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n\n<tool_call>\n<function=' + tc.name + '>\n' }}
+                {%- endif %}
+                {%- if tc.arguments is defined and tc.arguments is not none %}
+                    {%- if tc.arguments is mapping %}
+                        {%- for args_name, args_value in tc.arguments.items() %}
+                            {{- '<parameter=' + args_name + '>\n' }}
+                            {%- if args_value is mapping or (args_value is sequence and args_value is not string) %}
+                                {%- set _av = args_value | tojson %}
+                            {%- else %}
+                                {%- set _av = args_value | string %}
+                            {%- endif %}
+                            {%- if max_tool_arg_chars > 0 and _av | length > max_tool_arg_chars %}
+                                {{- _av[:max_tool_arg_chars] + '\n[TRUNCATED — original length ' ~ (_av | length | string) ~ ' chars]' }}
+                            {%- else %}
+                                {{- _av }}
+                            {%- endif %}
+                            {{- '\n</parameter>\n' }}
+                        {%- endfor %}
+                    {%- elif tc.arguments is string and tc.arguments %}
+                        {{- tc.arguments }}
+                    {%- endif %}
+                {%- endif %}
+                {%- if loop.last %}
+                    {{- '</function>\n</tool_call>\n' }}
+                {%- else %}
+                    {{- '</function>\n</tool_call>' }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == 'tool' %}
+        {%- set _content_lower = content | lower %}
+        {%- if content | length < 500 and '$ ' not in content and 'took ' not in _content_lower and ('"error":' in _content_lower or 'error:' in _content_lower or 'exception:' in _content_lower or 'traceback' in _content_lower or 'command not found' in _content_lower or 'invalid syntax' in _content_lower or 'failed to' in _content_lower) %}
+            {%- set ns2.consecutive_failures = ns2.consecutive_failures + 1 %}
+        {%- else %}
+            {%- set ns2.consecutive_failures = 0 %}
+        {%- endif %}
+        {%- if ns2.prev_role != 'tool' %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {%- if max_tool_response_chars > 0 and content | length > max_tool_response_chars %}
+            {%- set content = content[:max_tool_response_chars] + '\n[TRUNCATED — original length ' ~ (content | length | string) ~ ' chars]' %}
+        {%- endif %}
+        {{- '\n<tool_response>\n' + content }}
+        {%- if ns2.consecutive_failures >= 2 %}
+            {{- '\n\n⚠️ SYSTEM WARNING: ' ~ ns2.consecutive_failures ~ ' consecutive tool errors detected. Your previous approach is incorrect. You MUST use a fundamentally different approach or corrected arguments.' }}
+        {%- elif ns2.consecutive_failures == 1 %}
+            {{- '\n\n⚠️ SYSTEM WARNING: The previous tool call returned an error. Diagnose the failure and retry with completely corrected arguments.' }}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- else %}
+            {%- set _next_role = _msgs[loop.index0 + 1].role %}
+            {%- if _next_role != 'tool' %}
+                {{- '<|im_end|>\n' }}
+            {%- endif %}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>user\n[' + message.role + ']: ' + content + '<|im_end|>\n' }}
+    {%- endif %}
+    {%- set ns2.prev_role = message.role %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if not ns_state.thinking %}
+        {{- '<think>\n</think>\n' }}
+    {%- elif ns2.consecutive_failures >= 2 %}
+        {{- '<think>\n</think>\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

mmproj-F32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a714ac5e8e15687371fc95a180953a29b732962f6616f791063ff127559412
+size 931145888