LLM EXPLORER 60,828 MODELS INDEXED

GPT Oss 120B MXFP4 Q8 by mlx-community

By mlx-community · 7308 downloads
HF Repo ↗ Copy URL

GPT Oss 120B MXFP4 Q8 is an open-source language model by mlx-community. Features: 120b LLM, VRAM: 63.7GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.24.

  4-bit   Base model:openai/gpt-oss-120b Base model:quantized:openai/gp...   Conversational   Gpt oss   Mlx   Q8   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/mlx-community/gpt-oss-120b-MXFP4-Q8 

GPT Oss 120B MXFP4 Q8 Parameters and Internals

LLM NameGPT Oss 120B MXFP4 Q8
Repository 🤗https://huggingface.co/mlx-community/gpt-oss-120b-MXFP4-Q8 
Base Model(s)  GPT Oss 120B   openai/gpt-oss-120b
Model Size120b
Required VRAM63.7 GB
Updated2026-07-23
Maintainermlx-community
Model Typegpt_oss
Model Files  5.3 GB: 1-of-13   5.2 GB: 2-of-13   5.2 GB: 3-of-13   5.2 GB: 4-of-13   5.2 GB: 5-of-13   5.2 GB: 6-of-13   5.2 GB: 7-of-13   5.2 GB: 8-of-13   5.2 GB: 9-of-13   5.2 GB: 10-of-13   5.2 GB: 11-of-13   5.2 GB: 12-of-13   1.2 GB: 13-of-13
Quantization Typeq8
Model ArchitectureGptOssForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.55.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size201088

Best Alternatives to GPT Oss 120B MXFP4 Q8

Best Alternatives
Context / RAM
Downloads
Likes
GPT Oss 120B MLX 8bit128K / 123.7 GB3780113
GPT Oss 120B Unsloth Bnb 4bit128K / 62.1 GB1021117
GPT Oss 120B MXFP4 Q4128K / 61.9 GB47396
GPT Oss 120B 4bit128K / 65.9 GB4419
GPT Oss 120B 3bit128K / 113.2 GB3906
GPT Oss 120B128K / 65.1 GB42329475068
GPT Oss 120B128K / 65.1 GB274222
BlueBerry 1128K / 233.5 GB1501
BlueBerry 2128K / 233.5 GB1431
BlueBerry 3128K / 233.5 GB1401
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gpt-oss-120b-MXFP4-Q8.