Qwen3.6-35B-A3B-FP8

Home/Models/Qwen/Qwen3.6-35B-A3B-FP8

Qwen/Qwen3.6-35B-A3B-FP8

kind: fp8
quant: fp8 (8-bit)
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen3.6-35B-A3B
provider: Qwen
license: apache-2.0
language: —
context: 262,144
library: transformers
vRAM (GB): —
size on disk: —
downloads: 7,819,997
likes: 329
created: —
last modified: 2026-04-24T02:39:23+00:00 (2026)
huggingface: https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8
tags: transformerssafetensorsqwen3_5_moeimage-text-to-textconversationalbase_model:Qwen/Qwen3.6-35B-A3Bbase_model:quantized:Qwen/Qwen3.6-35B-A3Blicense:apache-2.0endpoints_compatiblefp8deploy:azureregion:us

benchmark	category	score	context	conf	evidence
Terminal-Bench	agentic-coding	2.0		medium	`Terminal-Bench 2.0`

title	author	status	type
how to quantize the model well?	Kekexu	open	disc
Listed on OpenModelMap	duola15	open	disc
Request: DOI	versatileYang	closed	disc
main	hanxin2000	draft	disc
main	hanxin2000	draft	disc
Qwen3.6-35B-A3B-FP8	RenqingZhao	draft	disc
Upload IMG-20260421-WA0030.jpg	jannybaby99	closed	disc
Performance degradation and looping behavior on long tasks with preserve_thinking enabled	ggenny	open	disc
Qwen3.6 test on Nvidia DGX Spark GB10	k3dani	open	disc
Qwen3.6 (vLLM) returns internal tool call and execution details in thinking stage	carmudi	closed	disc
Thank you and one ask.	AImhotep	open	disc
Overthinking issue	rex099	open	disc
Missing starting thinking tag	sayed0am	open	disc
will there be gptq int4 quan weights?	wangruiai2023	open	disc
Where's 397b?	ebfio	open	disc
Thank you Qwen you are the bests 3.6	pablohassan	open	disc