Skip to content

eemin

Qwen3.8-27B-NVFP4-MTP-2x16GB

eemin/Qwen3.8-27B-NVFP4-MTP-2x16GB

Qwen3.8-27B-NVFP4-MTP-2x16GB is a text generation model from eemin. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.

A self-quantized NVFP4 build of Qwen3.8-27B with speculative decoding via the model's own MTP head, deployed on two consumer 16 GB cards (2× RTX 5070 Ti) with vLLM tensor parallelism — reaching a genuine 150,000-token…

Downloads · 30 days

33

10% of all-time downloads

All-time downloads

329

Public

Parameters

18.6B

21.9 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors21.9 GB · 100%

Parameter types

How the weights are stored.

U89.2B · 49%

Try a prompt

Base models

Task
Text Generation
Type
qwen3_5
License
apache-2.0
Languages
en
Created
Aug 19, 2026
Updated
Aug 19, 2026