LLM EXPLORER 62,155 MODELS INDEXED

Qwen3.8 27B PARO MXFP6 by hugypufy

By hugypufy · 74 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B PARO MXFP6 is an open-source language model by hugypufy. Features: 27b LLM, VRAM: 25.1GB, License: apache-2.0, LLM Explorer Score: 0.28.

  6-bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Endpoints compatible   Image-text-to-text   Mxfp6   Paroquant   Paroquant mxfp6   Quantized   Qwen3 5   Rdna4   Region:us   Rocm   Safetensors   Sharded   Tensorflow   Vllm   W6a8
Model Card on HF 🤗: https://huggingface.co/hugypufy/Qwen3.8-27B-PARO-MXFP6 

Qwen3.8 27B PARO MXFP6 Parameters and Internals

LLM NameQwen3.8 27B PARO MXFP6
Repository 🤗https://huggingface.co/hugypufy/Qwen3.8-27B-PARO-MXFP6 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM25.1 GB
Updated2026-09-25
Maintainerhugypufy
Model Typeqwen3_5
Model Files  2.1 GB: 1-of-18   1.2 GB: 2-of-18   2.5 GB: 3-of-18   1.6 GB: 4-of-18   0.8 GB: 5-of-18   1.6 GB: 6-of-18   0.8 GB: 7-of-18   1.6 GB: 8-of-18   0.8 GB: 9-of-18   1.6 GB: 10-of-18   0.8 GB: 11-of-18   1.6 GB: 12-of-18   0.8 GB: 13-of-18   1.6 GB: 14-of-18   0.8 GB: 15-of-18   1.6 GB: 16-of-18   0.8 GB: 17-of-18   2.5 GB: 18-of-18
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B PARO MXFP6

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB1651
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.5 27B0K / 55.2 GB25362941028
Qwen3.6 27B FP80K / 0.4 GB7740472342
Note: green Score (e.g. "73.2") means that the model is better than hugypufy/Qwen3.8-27B-PARO-MXFP6.