Downloads · 30 days
262
31% of all-time downloads
Qwen3.8-27B-DFlash2-NVFP4-modelopt
hamichok/Qwen3.8-27B-DFlash2-NVFP4-modelopt
Qwen3.8-27B-DFlash2-NVFP4-modelopt is a machine learning model from hamichok. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Re-quantized DFlash2 draft for sglang's DFLASH speculative decoding, used by hamichok/Qwen3.8-27B-NVFP4-RTX5090-LMHead4.
All-time downloads
855
Public
Repo size
1.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Aug 29, 2026
- Updated
- Aug 29, 2026
- SHA
- 9e928357
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B-DFlash2-NVFP4-modelopt
Re-quantized DFlash2 draft for sglang's DFLASH speculative decoding, used by
hamichok/Qwen3.8-27B-NVFP4-RTX5090-LMHead4.
This is a re-quantization of incoai/Qwen3.8-27B-DFlash2 (BF16) to
modelopt-NVFP4 so sglang can load it as a speculative draft. The upstream
compressed-tensors NVFP4 variant does not load in sglang; this one does.
Why this exists
- DFLASH needs a draft the target
lm_head-quantized checkpoint can verify; the quantized head breaks DSPARK but not DFLASH. fcand q/k/v stay dense; onlyo_proj+ MLP projections are quantized (thedflash.pyloader shape-checksfc.weightas dense).
Usage (serve command)
Point --speculative-draft-model-path at this repo and
--speculative-draft-model-quantization modelopt_fp4, with
--speculative-dflash-block-size 6 (measured throughput peak). See the main
model card for the full recipe and measurements.
Provenance
Built with quantize-dflash2.py (Apache-2.0, from the main recipe repo).
Base: incoai/Qwen3.8-27B-DFlash2 (Apache-2.0).
- Type
- qwen3
- License
- apache-2.0
- Created
- Aug 29, 2026
- Updated
- Aug 29, 2026