gpt-oss-120b-GGUF
- https://huggingface.co/openai/gpt-oss-120b - https://huggingface.co/nvidia/gpt-oss-120b-Eagle3-v3
Params
120.0 B
Context
131,072
Downloads 30d
306 K
Likes
84
Download history
daily snapshots · 64 days
▲ 106 K in the last 30 days (53.3%)
306 K164 K
Oct 12Oct 22Nov 1Nov 10
306 K164 K
Sep 8Sep 29Oct 20Nov 10
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 |
|---|---|---|---|---|
| eagle3-gpt-oss-120b-Q8_0.gguf | Q8_0 | 0.8 GB | 19.4 GB | ✅ Runs comfortably |
| gpt-oss-120b-MXFP4.gguf | GGUF | 63.4 GB | 88.2 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$ ollama run gpt-oss-120b-gguf # pin the quantization explicitly $ ollama run gpt-oss-120b-gguf-gguf
$ huggingface-cli download ggml-org/gpt-oss-120b-GGUF-GGUF \
gpt-oss-120b-MXFP4.gguf --local-dir .
$ llama-cli -m gpt-oss-120b-MXFP4.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/gpt-oss-120b-gguf
{
"hf_id": "ggml-org/gpt-oss-120b-GGUF",
"params_b": 120.00,
"context_length": 131072,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 306072,
"vram_estimates": [
{ "quant": "GGUF", "gb": 88.2 },
{ "quant": "Q8_0", "gb": 19.4 }
],
"updated_at": "2026-10-20T01:00:21Z"
}
Specifications
- Parameters
- 120.0 B
- Context length
- 131,072
- Licence
- apache-2.0
- First seen on the Hub
- 2025-08-02
- Base model
- gpt-oss-120b
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-08
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model