Qwen3.6-27B-FP8

Home/Models/Qwen/Qwen3.6-27B-FP8

Qwen/Qwen3.6-27B-FP8

kind: fp8
quant: fp8 (8-bit)
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen3.6-27B
provider: Qwen
license: apache-2.0
language: —
context: 262,144
library: transformers
vRAM (GB): —
size on disk: —
downloads: 7,072,045
likes: 327
created: —
last modified: 2026-04-24T02:39:18+00:00 (2026)
huggingface: https://huggingface.co/Qwen/Qwen3.6-27B-FP8
tags: transformerssafetensorsqwen3_5image-text-to-textconversationalbase_model:Qwen/Qwen3.6-27Bbase_model:quantized:Qwen/Qwen3.6-27Blicense: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
Listed on OpenModelMap	duola15	open	disc
Update README.md	Dev8ng	open	disc
Update README.md	Dev8ng	open	disc
qwen3.6	dagezh	closed	disc
Any hope for a dynamic version of this model?	mirix	open	disc
Performance report on RTX 4090D (48GB VRAM): 40 t/s	SlavikF	open	disc
Cannot run on RTX PRO 6000 Blackwell + WSL2 — Mamba state cache OOM	noMugop	open	disc
The response from SGLang 0.5.10.post1 is garbled.	zhazhahui080507	open	disc
Garbage output	andylele	closed	disc
Just want to say thank you	Thyrannius	closed	disc
SGLang --speculative-algorithm NEXTN or EAGLE?	pathosethoslogos	open	disc
VLLM warning about Using uncalibrated q_scale 1.0 and/or prob_scale 1.0 with fp8 attention	androiddrew	open	disc
NVFP4	celikburak	open	disc
Parameter model.layers.15.mlp.gate_gate_up_proj.weight_scale_inv not found in params_dict	CHNtentes	open	disc
[Question] Can the model be run on Nvidia DGX Spark?	hubertshelley	open	disc
About this FP8	sudo-0x2a	closed	disc