Qwen3.8-27B NVFP4, trained with QUASAR
19.7 GB · 496/496 transformer linears in NVFP4 (W4A4) · 0.909 GPQA-Diamond vs. 0.914 BF16 · serves directly with vLLM.
Among the public NVFP4 builds compared below, QUASAR is both the smallest and the highest-scoring: 90.9 GPQA-Diamond and 100% AIME'26.
Independent evaluation: A third-party NVFP4 shootout on the official Qwen3.8-27B repo compares QUASAR against other public NVFP4 checkpoints under the same evaluation and serving setup.
Smaller sibling — Qwen3.5-4B: W4A16 / vLLM · W4A4 / Blackwell · Q4_0 GGUF / llama.cpp · collection · paper
More QUASAR checkpoints: Gemma 4 collection · Muse-Glimmer collection · paper.
QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4 is a 4-bit NVFP4 version of
Qwen/Qwen3.8-27B, produced with
QUASAR, a quantization-aware training (QAT) method.
QUASAR trains the NVFP4 weights directly against the frozen BF16 model, then exports standard NVFP4 weights with no custom inference path. This lets us quantize all 496 transformer linears—including attention and gated delta-net—to NVFP4 while preserving near-BF16 quality: the smallest of the compared public NVFP4 builds, while scoring highest among them on both GPQA-Diamond and AIME'26.
📄 Paper: QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction
How to run
Compatible with vLLM, with no conversion step:
pip install "vllm>=0.27"
vllm serve QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4 \
--max-model-len 262144 \
--gpu-memory-utilization 0.85 \
--max-num-seqs 512 \
--speculative-config '{"method": "mtp", "num_speculative_tokens": 2}' \
--enable-auto-tool-choice --tool-call-parser qwen3_xml \
--reasoning-parser qwen3
On a 32 GB card such as an RTX 5090, lower the context to --max-model-len 65536.
Requires an NVIDIA GPU with FP4 support (Blackwell, compute capability 10.0+).
Quality and size comparison
Two other public NVFP4 builds of this model, evaluated under the same setup (GPQA-Diamond: 2 runs, n=396; AIME'26: 3 repeats, n=90). Bold = best among the NVFP4 builds.
| Model | Size | NVFP4 linears | GPQA-D | AIME'26 |
|---|---|---|---|---|
| QUASAR (this model) | 19.7 GB | 496/496 | 90.91 | 100.0 |
| BF16 original | 55.6 GB | — | 91.41 | 100.0 |
| Unsloth NVFP4 | 23.4 GB | 168/496 | 89.39 | 97.78 |
| Inferact NVFP4 | 26.4 GB | 304/496 | 87.63 | 96.67 |
| Model | MRCR | MRCR 8-needle | HMMT'26 | SuperGPQA | LiveCodeBench | RULER 32K | RULER 64K | RULER 128K |
|---|---|---|---|---|---|---|---|---|
| QUASAR (this model) | 79.1 | 52.7 | 73.4 | 62.4 | 79.2 | 96.3 | 96.2 | 95.8 |
| BF16 original | 83.4 | 58.5 | 75.8 | 63.0 | 81.0 | 96.7 | 96.6 | 95.9 |
| GPTQ NVFP4 (LLM Compressor, ours) | 61.3 | 35.5 | 69.7 | 58.9 | 77.9 | 96.0 | 95.4 | 95.3 |
| RTN NVFP4 (LLM Compressor, ours) | 57.3 | 32.8 | 66.9 | 58.6 | 77.9 | 96.2 | 96.1 | 95.3 |
Training
One epoch of loss-aware NVFP4 quantization-aware distillation against the frozen BF16 teacher: global batch size 32, learning rate 1e-6, 2446 steps.
Citation
@article{counathe2026quasar,
title={QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction},
author={Counathe, Vincent and Athiwaratkun, Ben and De Sa, Christopher and Zhang, Tianyi},
journal={arXiv preprint arXiv:2608.13966},
year={2026}
}