Six open-weight quants: add Ornith-1.5 and Nemotron-3.5-Lightning, two-row lineup chart

README.md

@@ -15,7 +15,7 @@ pinned: false
   <a href="https://primitive.com"><img src="https://img.shields.io/badge/web-primitive.com-F98424?style=flat-square" alt="primitive.com"></a>
   <img src="https://img.shields.io/badge/focus-inference%20economics-F98424?style=flat-square" alt="Inference economics">
   <img src="https://img.shields.io/badge/runtimes-vLLM%20·%20ONNX-F98424?style=flat-square" alt="vLLM and ONNX">
-  <img src="https://img.shields.io/badge/open%20weights-4%20models-3DD13D?style=flat-square" alt="Four open-weight models">
+  <img src="https://img.shields.io/badge/open%20weights-6%20models-3DD13D?style=flat-square" alt="Six open-weight models">
 </p>
 
 ---
@@ -53,17 +53,17 @@ already have, not just the newest ones.
 
 ---
 
-## Out now: four open-weight quants
+## Out now: six open-weight quants
 
 <p align="center">
-  <img src="assets/lineup.png" alt="Across the four public quants: 2.5× to 3.4× smaller than BF16; 2.00× to 2.40× BF16 throughput at concurrency 32; accuracy within ±0.3 points of BF16, inside the ±0.8 run-to-run band — ties, not wins" width="100%">
+  <img src="assets/lineup.png" alt="Across the six public quants: 2.5× to 3.4× smaller than BF16; 1.72× to 2.68× BF16 throughput at concurrency 32; accuracy within 0.5 points of BF16 in either direction, inside the ±0.8 run-to-run band — ties, not wins" width="100%">
 </p>
 
 Weights-only mixed precision, `compressed-tensors`, stock `vllm serve`. Every
 figure below is on the model's own card, next to the run that produced it.
 
 * 🧮 **[Qwen3.8-27B — mixed NVFP4/FP8](https://huggingface.co/primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8)**
-  · ~21 GiB, **2.5× smaller than BF16** and 27% smaller than Qwen's own FP8, with
+  · 20.7 GiB, **2.5× smaller than BF16** and 28% smaller than Qwen's own FP8, with
   accuracy tied to BF16 (88.5 vs 88.6 — and the same weights re-scored 87.5 in a
   second sitting, which is what a tie looks like). **Loads on an A100**, not just
   Blackwell, and the in-checkpoint MTP head survives, so speculative decoding
@@ -73,12 +73,24 @@ figure below is on the model's own card, next to the run that produced it.
   official quant** — while running faster than all of them at 3,268 tok/s.
 * 🐘 **[Laguna-S-2.1 — mixed NVFP4/MXFP8](https://huggingface.co/primitive-ai/Laguna-S-2.1-mixed-NVFP4-MXFP8)**
   · 219 GB of source weights down to 64 GiB at 4.67 bits/weight — **it serves
-  from one 96 GiB GPU**, with +25% single-stream decode over poolside's own NVFP4
-  at a smaller footprint.
+  from one 96 GiB GPU**, the smallest and fastest of the 4-bit field, with +23%
+  single-stream decode over the NVFP4 alternative at a 3 GiB smaller footprint.
 * 👁️ **[Muse-Glimmer-30B — mixed NVFP4](https://huggingface.co/primitive-ai/Muse-Glimmer-30B-mixed-NVFP4)**
   · A vision-language model at 20.4 GiB, **2.40× BF16 throughput** and 86.0
   against BF16's 86.2. **The vision tower stays BF16** — a VLM loses its visual
   grounding before it loses its words.
+* 🦅 **[Ornith-1.5-35B-A3B — mixed NVFP4/FP8](https://huggingface.co/primitive-ai/Ornith-1.5-35B-A3B-mixed-NVFP4-FP8)**
+  · A 35 B MoE vision-language model at 22.6 GiB, **3.0× smaller than BF16** and
+  39% smaller than the official FP8, scoring 91.5 against BF16's 92.0 — the only
+  quant of this model we have measured level with BF16. **The official NVFP4 is
+  faster and 0.75 GiB smaller**; this build trades that for the closest accuracy
+  to BF16 and a BF16 output head that keeps the Ampere path loadable.
+* ⚡ **[Nemotron-3.5-Lightning-30B-A3B — mixed INT4/INT8](https://huggingface.co/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8)**
+  · A MoE+Mamba hybrid at 19.2 GiB and 5.01 bits/weight, **3.3× smaller than
+  BF16 at 2.7× its throughput** — and **8.6% smaller and ~7.7% faster than
+  nvidia's own NVFP4**, from weights-only round-to-nearest with no calibration
+  data. We make no accuracy claim here: identical weights scored 88.0 and 87.4
+  on two runs, so that column is a tie.
 
 ---
 
@@ -124,11 +136,14 @@ squeezing a large checkpoint onto GPUs you already own.
 | `Laguna-XS-2.1-mixed-NVFP4-MXFP8` | Mixed-precision quant of poolside's Laguna-XS-2.1. Smallest and fastest build of it we've measured. | **Open weights** |
 | `Laguna-S-2.1-mixed-NVFP4-MXFP8` | Mixed-precision quant of poolside's Laguna-S-2.1. 219 GB of weights onto a single 96 GiB card. | **Open weights** |
 | `Muse-Glimmer-30B-mixed-NVFP4` | NVFP4 quant of the Muse-Glimmer-30B VLM, GPTQ-calibrated. Vision tower left at BF16. | **Open weights** |
+| `Ornith-1.5-35B-A3B-mixed-NVFP4-FP8` | Mixed-precision quant of Ornith-1.5-35B-A3B, a 35 B MoE VLM. Vision tower and MTP block left at BF16. | **Open weights** |
+| `Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8` | INT4/INT8 quant of nvidia's MoE+Mamba hybrid. Smaller and faster than the official NVFP4, no calibration data. | **Open weights** |
 | `llm-router-lite-80m-onnx` | CPU-only router: reads a chat `messages` array, ranks which LLM to call. ONNX, no torch or transformers. | Private beta |
 
 Published weights carry their upstream licence — Apache-2.0 for the Qwen and
-Muse-Glimmer builds, OpenMDW-1.1 for the Laguna builds. Derivative models carry
-upstream attribution and a `NOTICE` or `LICENSE` file.
+Muse-Glimmer builds, OpenMDW-1.1 for the Laguna and Nemotron builds, MIT for the
+Ornith build. Derivative models carry upstream attribution and a `NOTICE` or
+`LICENSE` file.
 
 ---