Instructions to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Use Docker

docker model run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Ollama
How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Ollama:
```
ollama run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
```
Unsloth Desktop

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Docker Model Runner:
```
docker model run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
```

Lemonade

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

lmcoleman commited on Jul 9

Commit

f1d183d

verified ·

1 Parent(s): f5066a6

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +18 -2

README.md CHANGED Viewed

@@ -27,12 +27,27 @@ every surviving candidate, imatrix-weighted encoding, and stream-aware sampling.
 tier's per-group precision layout was selected from 16 fully-measured candidate hybrids
 rather than applied uniformly.
-> **Text-only.** The base is a Qwen3.5-VL vision-language model; the vision tower was
-> dropped during conversion, so these are text (LLM) quants — no image input.
 The embedded **MTP (multi-token-prediction) head** is preserved, so these work with
 llama.cpp speculative decoding using the *same file* as its own draft model.
 ## Files
 | File | Size | PPL (wikitext-2) | vs BF16 baseline (6.7803) | Layout |
@@ -62,6 +77,7 @@ llama-server -m ThinkingCap-Qwen3.6-27B-Q4_K_M.gguf \
 - Chat template is embedded (no patching needed); architecture `qwen35`.
 - Group legend: E=embeddings, H=lm head, Q/K/O=attention, U/D=FFN up/down, S=SSM (mamba) ops.
 - This is a hybrid (linear-attention + attention) architecture; SSM conv/1D tensors are
   kept at F32 where the block size requires it.
 - Sibling repo with AMD-native (ROCmFPX fork-only) builds of the same layouts:

 tier's per-group precision layout was selected from 16 fully-measured candidate hybrids
 rather than applied uniformly.
+> **Vision-capable.** The base is a Qwen3.5-VL vision-language model. These GGUFs are the
+> quantized **text** model; pair any of them with the included
+> `mmproj-ThinkingCap-Qwen3.6-27B-f16.gguf` (the f16 vision projector, 0.86 GiB) to run
+> image input. Verified end-to-end (image description) with the Q4 quant + this mmproj.
 The embedded **MTP (multi-token-prediction) head** is preserved, so these work with
 llama.cpp speculative decoding using the *same file* as its own draft model.
+## Vision (image input)
+Serve any tier with the vision projector:
+```bash
+llama-server -m ThinkingCap-Qwen3.6-27B-Q4_K_M.gguf \
+  --mmproj mmproj-ThinkingCap-Qwen3.6-27B-f16.gguf \
+  -c 8192 -ngl 99 -fa on
+```
+Then send images via the OpenAI-compatible `image_url` content field. (MTP speculative
+decoding and vision can each be enabled; combine flags as needed.)
 ## Files
 | File | Size | PPL (wikitext-2) | vs BF16 baseline (6.7803) | Layout |
 - Chat template is embedded (no patching needed); architecture `qwen35`.
 - Group legend: E=embeddings, H=lm head, Q/K/O=attention, U/D=FFN up/down, S=SSM (mamba) ops.
+- `mmproj-*-f16.gguf` (0.86 GiB) is the vision projector — required only for image input.
 - This is a hybrid (linear-attention + attention) architecture; SSM conv/1D tensors are
   kept at F32 where the block size requires it.
 - Sibling repo with AMD-native (ROCmFPX fork-only) builds of the same layouts: