What are the hardware requirements for GPT Oss 120B MLX 8bit?

GPT Oss 120B MLX 8bit requires approximately 123.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GPT Oss 120B MLX 8bit and how large is it?

GPT Oss 120B MLX 8bit is developed by lmstudio-community, a model with 120b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate GPT Oss 120B MLX 8bit?

GPT Oss 120B MLX 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GPT Oss 120B MLX 8bit by lmstudio-community — VRAM 123.7GB, 128K context

Name: GPT Oss 120B MLX 8bit
Author: lmstudio-community

GPT Oss 120B MLX 8bit is an open-source language model by lmstudio-community. Features: 120b LLM, VRAM: 123.7GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.26.

8-bit 8bit Base model:openai/gpt-oss-120b Base model:quantized:openai/gp... Conversational Endpoints compatible Gpt oss Mlx Quantized Region:us Safetensors Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/lmstudio-community/gpt-oss-120b-MLX-8bit

GPT Oss 120B MLX 8bit Parameters and Internals

LLM Name	GPT Oss 120B MLX 8bit
Repository 🤗	https://huggingface.co/lmstudio-community/gpt-oss-120b-MLX-8bit
Base Model(s)	GPT Oss 120B openai/gpt-oss-120b
Model Size	120b
Required VRAM	123.7 GB
Updated	2026-07-23
Maintainer	lmstudio-community
Model Type	gpt_oss
Model Files	5.2 GB: 1-of-27 4.5 GB: 2-of-27 4.6 GB: 3-of-27 4.5 GB: 4-of-27 4.5 GB: 5-of-27 4.6 GB: 6-of-27 4.5 GB: 7-of-27 4.5 GB: 8-of-27 4.6 GB: 9-of-27 4.5 GB: 10-of-27 4.5 GB: 11-of-27 4.6 GB: 12-of-27 4.5 GB: 13-of-27 4.5 GB: 14-of-27 4.6 GB: 15-of-27 4.5 GB: 16-of-27 4.5 GB: 17-of-27 4.6 GB: 18-of-27 4.5 GB: 19-of-27 4.5 GB: 20-of-27 4.6 GB: 21-of-27 4.5 GB: 22-of-27 4.5 GB: 23-of-27 4.6 GB: 24-of-27 4.5 GB: 25-of-27 4.5 GB: 26-of-27 5.2 GB: 27-of-27
Quantization Type	8bit
Model Architecture	GptOssForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.55.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	201088

Rank the GPT Oss 120B MLX 8bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to GPT Oss 120B MLX 8bit

Best Alternatives	Context / RAM	Downloads	Likes
GPT Oss 120B Unsloth Bnb 4bit	128K / 62.1 GB	10211	17
GPT Oss 120B MXFP4 Q8	128K / 63.7 GB	7308	17
GPT Oss 120B MXFP4 Q4	128K / 61.9 GB	4739	6
GPT Oss 120B 4bit	128K / 65.9 GB	441	9
GPT Oss 120B 3bit	128K / 113.2 GB	390	6
GPT Oss 120B	128K / 65.1 GB	4232947	5068
GPT Oss 120B	128K / 65.1 GB	2742	22
BlueBerry 1	128K / 233.5 GB	150	1
BlueBerry 2	128K / 233.5 GB	143	1
BlueBerry 3	128K / 233.5 GB	140	1

Note: green Score (e.g. "73.2") means that the model is better than lmstudio-community/gpt-oss-120b-MLX-8bit.