Qwen3.8-27B DFlash2 MXFP4 MLX
An unofficial MLX MXFP4 conversion of
incoai/Qwen3.8-27B-DFlash2,
produced for Apple Silicon speculative decoding with
oMLX. It is a quantized conversion, not a
fine-tune, merge, retraining, or new DFlash model. It is not affiliated with
or endorsed by Inco AI or Qwen.
This is not a standalone chat model. It is a DFlash2 draft sidecar for the matching
Qwen/Qwen3.8-27Btarget architecture. The large target model remains responsible for verifying every drafted token and producing the final output.
Conversion
| Setting | Value |
|---|---|
| Source | incoai/Qwen3.8-27B-DFlash2 |
| Conversion tool | mlx_vlm.convert |
| Weight format | MXFP4 |
| Nominal bits | 4 |
| Group size | 32 |
| Non-quantized dtype | BF16 |
| Resulting disk size | approximately 1 GB |
The conversion command was:
mlx_vlm.convert \
--hf-path incoai/Qwen3.8-27B-DFlash2 \
--quantize \
--q-bits 4 \
--q-mode mxfp4 \
--q-group-size 32 \
--dtype bfloat16 \
--mlx-path Qwen3.8-27B-DFlash2-mxfp4
What DFlash2 does
DFlash2 is a speculative-decoding drafter. It predicts a short block of likely next tokens; the full Qwen3.8-27B target verifies them and accepts only the tokens that match. This can reduce the number of expensive target-model decode passes without changing the target model's authority over the output.
Actual speedup depends on the prompt, sampling settings, context length, and draft acceptance rate. It does not improve prompt-prefill speed.
Use with oMLX
Use this as the DFlash draft for a separately downloaded Qwen3.8-27B target,
such as deresolution/Qwen3.8-27B-mxfp4.
In the target model's oMLX profile:
- Enable DFlash.
- Choose this model as the draft model.
- Disable runtime draft quantization because this checkpoint is already MXFP4-quantized.
- Set DFlash block size to 5 for this quantized target/draft pairing.
- Do not enable Lightning MTP and DFlash at the same time.
Keep this sidecar unloaded as a standalone model in oMLX's model library. The target's DFlash engine attaches it internally when the target is loaded.
Compatibility
This conversion was tested as the draft sidecar for the Qwen3.8-27B MXFP4 target above on a 32 GB Apple Silicon Mac using oMLX. It is not a general purpose MLX chat checkpoint and is not expected to work as a draft for other Qwen families or unrelated targets.
For the DFlash algorithm and upstream benchmark details, see the DFlash repository, the upstream DFlash2 model card, and oMLX's experimental DFlash integration guide.
License and attribution
This derivative conversion retains the upstream Apache License 2.0. Please refer to the upstream DFlash2 model card for intended use, limitations, evaluation, and citation information.