openai / text-generation updated 11 months ago

gpt-oss-120b

Name: gpt-oss-120b
Author: openai

Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

Params

120.4 B

Context

131,072

Downloads 30d

4.2 M

Likes

5,079

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

4.3 M4.2 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	u8	130.5 GB	162.1 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 128K ctx	130.5 GB	433.0 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/gpt-oss-120b
{
  "hf_id": "openai/gpt-oss-120b",
  "params_b": 120.41,
  "context_length": 131072,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 4221708,
  "vram_estimates": [
    { "quant": "u8", "gb": 162.1 }
  ],
  "updated_at": "2026-07-28T17:06:58Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: GptOssForCausalLM
Parameters: 120.4 B
Tensor type: U8
Context length: 131,072
Vocabulary: 201,088
Layers / heads: 36 / 64
Licence: apache-2.0
First seen on the Hub: 2025-08-04
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 2.8 M DeepSeek-V4-Flash 2.7 M Qwen3-Coder-Next-FP8 2.2 M Qwen-72B 2.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB