LLM EXPLORER 57,918 MODELS INDEXED

GPT Oss 120B 4bit by mlx-community

By mlx-community · 441 downloads
HF Repo ↗ Copy URL

GPT Oss 120B 4bit is an open-source language model by mlx-community. Features: 120b LLM, VRAM: 65.9GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.2.

  4-bit   4bit   Conversational   Endpoints compatible   Gpt oss   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/mlx-community/gpt-oss-120b-4bit 

GPT Oss 120B 4bit Parameters and Internals

LLM NameGPT Oss 120B 4bit
Repository 🤗https://huggingface.co/mlx-community/gpt-oss-120b-4bit 
Model Size120b
Required VRAM65.9 GB
Updated2026-07-16
Maintainermlx-community
Model Typegpt_oss
Model Files  5.2 GB: 1-of-13   5.4 GB: 2-of-13   4.9 GB: 3-of-13   5.4 GB: 4-of-13   4.9 GB: 5-of-13   5.3 GB: 6-of-13   4.9 GB: 7-of-13   5.4 GB: 8-of-13   4.9 GB: 9-of-13   5.4 GB: 10-of-13   4.9 GB: 11-of-13   5.3 GB: 12-of-13   4.0 GB: 13-of-13
Quantization Type4bit
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 4bit

Best Alternatives
Context / RAM
Downloads
Likes
GPT Oss 120B MLX 8bit128K / 123.7 GB3780113
GPT Oss 120B MXFP4 Q8128K / 63.7 GB730817
GPT Oss 120B Unsloth Bnb 4bit128K / 62.1 GB1021117
GPT Oss 120B MXFP4 Q4128K / 61.9 GB47396
GPT Oss 120B 3bit128K / 113.2 GB3906
GPT Oss 120B128K / 65.1 GB42329475068
GPT Oss 120B128K / 65.1 GB274222
GPT Oss 120B GGUF128K / 65.4 GB107592287
GPT Oss 120B Mxfp4 Bf16128K / 64.8 GB16532
Medical GPT OSS Swallow 120B128K / 139.8 GB1394
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gpt-oss-120b-4bit.