LLM EXPLORER 58,531 MODELS INDEXED

Qwen3.8 27B MTPLX Bare Speed by Youssofal

By Youssofal · 6 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B MTPLX Bare Speed is an open-source language model by Youssofal. Features: 27b LLM, VRAM: 15.1GB, License: apache-2.0, LLM Explorer Score: 0.31.

  4-bit   Apple-silicon Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Chat   Conversational   Local-ai   Macos   Mlx   Mtp   Mtplx   Multi-token-prediction   Qwen   Qwen3.8   Qwen3 5   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed 

Qwen3.8 27B MTPLX Bare Speed Parameters and Internals

LLM NameQwen3.8 27B MTPLX Bare Speed
Repository 🤗https://huggingface.co/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM15.1 GB
Updated2026-08-15
MaintainerYoussofal
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   4.5 GB: 3-of-3   0.8 GB
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 MTPLX Bare Speed

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.8 27B NVFP40K / 22 GB3012214
ThinkingCap Qwen3.6 27B0K / 54.7 GB35947614
Qwen3.8 27B INT8 W8A16 MTP0K / 30.7 GB472326
Qwen3.6 27B FP80K / 0.4 GB7740472342
Qwen3.8 27B Heretic Ara0K / 54.6 GB84146
Qwen3.5 27B0K / 55.2 GB25362941028
Note: green Score (e.g. "73.2") means that the model is better than Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed.