Downloads · 30 days
23
8% of all-time downloads
manishkumar2101114/qwen3.6-35b-a3b-tool-merged-fp8
qwen3.6-35b-a3b-tool-merged-fp8 is a image-text-to-text model from manishkumar2101114. Use it for the image-text-to-text 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.
Base: Qwen/Qwen3.6-35B-A3B-FP8 (same FP8 block format/scales convention). Adapter: qwen3.6-35b-a3b-tool-adapter-sglang (LoRA r=32, 3 epochs, 1515 tool-call dialogues). Merged in BF16 (train loss 0.2029 / eval 0.2047),…
Downloads · 30 days
23
8% of all-time downloads
All-time downloads
281
Public
Parameters
36B
37.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors37.5 GB · 100%
How the weights are stored.
F8_E4M334.5B · 96%
From the Hugging Face model README
Base: Qwen/Qwen3.6-35B-A3B-FP8 (same FP8 block format/scales convention). Adapter: qwen3.6-35b-a3b-tool-adapter-sglang (LoRA r=32, 3 epochs, 1515 tool-call dialogues). Merged in BF16 (train loss 0.2029 / eval 0.2047), then block-requantized to FP8 e4m3/128. Chat template: qwen3_template333.jinja. Serve with sglang / vllm / transformers.