Home / Models / Gpt Oss 120B
OpenAI

Gpt Oss 120B

Gpt Oss 120B is an open-weights 120B-parameter model by OpenAI. It holds an Intelligence score of 55.5 on the local.ai leaderboard (2026-08 snapshot).

open weights
55.5
local.ai Intelligence
Parameters
120B
Benchmarks (local.ai snapshot)
τ²-bench
65%
GAIA
56%
GDPval
53%
HuggingFace metadata · updated 2025-08-26
repo
openai/gpt-oss-120b
license
apache-2.0
downloads
4,444,318
likes
5,103
Official HuggingFace repoOllamaCompare on the savings tool

Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.

Does it fit your hardware?

Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.

Q4_K_M 69.6GQ6_K 108GQ8_0 132GFP16 240G
Quantization≈ File sizeNote
IQ2_XXS32.4 GBExtreme compression, largest quality loss
IQ3_XXS43.2 GBVery small
Q3_K_M55.2 GBSmall
NVFP460 GBNVIDIA 4-bit
Q4_K_S64.8 GBCommon
Q4_K_M69.6 GBMost common sweet spot
Q5_K_M91.2 GBBalanced
Q6_K108 GBNear-lossless
Q8_0132 GBNear-lossless
FP16240 GBOriginal weights

Actual files on HuggingFace

FileSize
metal/model.bin60.76 GB
original/model--00001-of-00007.safetensors9.82 GB
original/model--00003-of-00007.safetensors9.77 GB
original/model--00002-of-00007.safetensors9.77 GB
original/model--00005-of-00007.safetensors9.77 GB
original/model--00004-of-00007.safetensors9.77 GB
GGUF: unsloth/gpt-oss-120b-GGUF · 108,720 downloads
FileSize
Q2_K/gpt-oss-120b-Q2_K-00001-of-00002.gguf46.06 GBdownload
Q2_K/gpt-oss-120b-Q2_K-00002-of-00002.gguf12.21 GBdownload
Q2_K_L/gpt-oss-120b-Q2_K_L-00001-of-00002.gguf46.33 GBdownload
Q2_K_L/gpt-oss-120b-Q2_K_L-00002-of-00002.gguf12.21 GBdownload
Q3_K_M/gpt-oss-120b-Q3_K_M-00001-of-00002.gguf46.10 GBdownload
Q3_K_M/gpt-oss-120b-Q3_K_M-00002-of-00002.gguf12.22 GBdownload
Q3_K_S/gpt-oss-120b-Q3_K_S-00001-of-00002.gguf46.06 GBdownload
Q3_K_S/gpt-oss-120b-Q3_K_S-00002-of-00002.gguf12.21 GBdownload
Q4_0/gpt-oss-120b-Q4_0-00001-of-00002.gguf46.10 GBdownload
Q4_0/gpt-oss-120b-Q4_0-00002-of-00002.gguf12.22 GBdownload
Q4_1/gpt-oss-120b-Q4_1-00001-of-00002.gguf46.18 GBdownload
Q4_1/gpt-oss-120b-Q4_1-00002-of-00002.gguf12.23 GBdownload
GGUF: ggml-org/gpt-oss-120b-GGUF · 57,288 downloads
FileSize
eagle3-gpt-oss-120b-BF16.gguf1.48 GBdownload
eagle3-gpt-oss-120b-Q8_0.gguf0.79 GBdownload
gpt-oss-120b-MXFP4.gguf59.03 GBdownload

What you save self-hosting this model

Uses the model's own API price when it exists; otherwise the closest commercial equivalent.

Waiting for hardware detection…

Related models

OpenAI
Gpt Oss 20B
20B params · Intelligence 43.3

RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.