LLM EXPLORER 61,652 MODELS INDEXED

GPT Oss 20B OptiQ 4bit by mlx-community

By mlx-community · 1690 downloads
HF Repo ↗ Copy URL

GPT Oss 20B OptiQ 4bit is an open-source language model by mlx-community. Features: 20b LLM, VRAM: 11.6GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.28.

  4-bit   4bit   Apple-silicon   Base model:openai/gpt-oss-20b Base model:quantized:openai/gp...   Conversational   En   Gpt-oss   Gpt oss   Mixed-precision   Mlx   Moe   Openai   Optiq   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/gpt-oss-20b-OptiQ-4bit 

GPT Oss 20B OptiQ 4bit Parameters and Internals

LLM NameGPT Oss 20B OptiQ 4bit
Repository 🤗https://huggingface.co/mlx-community/gpt-oss-20b-OptiQ-4bit 
Base Model(s)  GPT Oss 20B   openai/gpt-oss-20b
Model Size20b
Required VRAM11.6 GB
Updated2026-07-31
Maintainermlx-community
Model Typegpt_oss
Model Files  5.4 GB: 1-of-3   5.3 GB: 2-of-3   0.9 GB: 3-of-3
Supported Languagesen
Quantization Type4bit
Model ArchitectureGptOssForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.55.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size201088

Best Alternatives to GPT Oss 20B OptiQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
GPT Oss 20B MXFP4 Q8128K / 12.1 GB3972
GPT Oss 20B MXFP4 Q8128K / 12.1 GB35442179
GPT Oss 20B Unsloth Bnb 4bit128K / 12.6 GB6491438
GPT Oss 20B 4bit128K / 13.8 GB181
...s 20B Ja Fin Thinking MLX 4bit128K / 11.8 GB1261
...s 20B Ja Fin Thinking MLX 8bit128K / 22.1 GB1021
GPT Oss 20B MLX 8bit128K / 22.1 GB289058
GPT Oss 20B MXFP4 Q4128K / 11.2 GB217816
GPT Oss 20B Bnb 4bit128K / 40.8 GB240214
GPT Oss Coder 20B128K / 13.8 GB1313
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gpt-oss-20b-OptiQ-4bit.