LLM EXPLORER 64,811 MODELS INDEXED

Qwen3.8 27B Redashes SSMFix INT8 W8A16 MTP by lued

By lued · 21 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B Redashes SSMFix INT8 W8A16 MTP is an open-source language model by lued. Features: 27b LLM, VRAM: 30.6GB, License: apache-2.0, LLM Explorer Score: 0.25.

Base model:quantized:redashes/... Base model:redashes/qwen3.8-27...   Compressed-tensors   Conv1d-repair   Conversational   Image-text-to-text   Int8   Mtp   Quantized   Qwen3.8   Qwen3 5   Region:us   Safetensors   Sharded   Speculative-decoding   Ssm-fix   Tensorflow   Vision   Vllm   W8a16
Model Card on HF 🤗: https://huggingface.co/lued/Qwen3.8-27B-redashes-SSMFix-INT8-W8A16-MTP 

Qwen3.8 27B Redashes SSMFix INT8 W8A16 MTP Parameters and Internals

LLM NameQwen3.8 27B Redashes SSMFix INT8 W8A16 MTP
Repository 🤗https://huggingface.co/lued/Qwen3.8-27B-redashes-SSMFix-INT8-W8A16-MTP 
Base Model(s)  redashes/Qwen3.8-27B-BF16-SSMFIX   redashes/Qwen3.8-27B-BF16-SSMFIX
Model Size27b
Required VRAM30.6 GB
Updated2026-08-20
Maintainerlued
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-7   5.3 GB: 2-of-7   5.3 GB: 3-of-7   3.9 GB: 4-of-7   5.3 GB: 5-of-7   5.3 GB: 6-of-7   0.2 GB: 7-of-7   0.8 GB
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B Redashes SSMFix INT8 W8A16 MTP

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB953
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB201602194
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.6 27B NVFP40K / 22 GB1887525419
Note: green Score (e.g. "73.2") means that the model is better than lued/Qwen3.8-27B-redashes-SSMFix-INT8-W8A16-MTP.