Downloads · 30 days
21
22% of all-time downloads
Ravionhf/qwen3.6-27b-reasoning-distill-fp8-v1
qwen3.6-27b-reasoning-distill-fp8-v1 is a image-text-to-text model from Ravionhf. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Qwen/Qwen3.6-27B (revision 6a9e13bd6fc8f0983b9b99948120bc37f49c13e9) with a merged QLoRA adapter trained on reasoning traces, re-quantized to FP8 for serving. Multimodal stack intact (image processor: Qwen2VLImageProc…
Downloads · 30 days
21
22% of all-time downloads
All-time downloads
96
Public
Parameters
27.4B
35.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors35.9 GB · 100%
How the weights are stored.
F8_E4M318.8B · 69%
From the Hugging Face model README
Qwen/Qwen3.6-27B (revision 6a9e13bd6fc8f0983b9b99948120bc37f49c13e9) with a
merged QLoRA adapter trained on reasoning traces, re-quantized to FP8 for serving.
Multimodal stack intact (image processor: Qwen2VLImageProcessorFast).
sft_balanced — teachers ~86 percent qwen3.8-max-preview, ~10 percent GLM-5.2,
~4 percent Kimi K3; domains reasoning / agent-tool / math / code / science;
verifier-failed rows dropped.BF16 merge (top-1 logit parity gate vs the pre-merge reference passed) →
llm-compressor FP8 static
per-tensor W8A8, calibrated on 96 on-distribution prompts. Linear-attention
sublayers, vision tower and lm_head stay BF16 (see recipe.yaml).
vllm serve <this-repo> --max-model-len 32768 \
--reasoning-parser qwen3 --tool-call-parser qwen3_coder
Thinking on: chat_template_kwargs={"enable_thinking": true},
temp 0.6 / top_p 0.95 / top_k 20.
v1 trained text-only (images placeholder-tokenized at train time; served multimodal). Small eval n; the adapter targets agentic tool-use reasoning and is not a general-purpose improvement claim.
Sibling repo: the unmerged adapter is published as
Ravionhf/qwen3.6-27b-reasoning-distill-lora-v1.