OpenAI
Gpt Oss 20B
Gpt Oss 20B is an open-weights 20B-parameter model by OpenAI. It holds an Intelligence score of 43.3 on the local.ai leaderboard (2026-08 snapshot).
open weights
43.3
local.ai Intelligence
Parameters
20B
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2025-08-26
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 11.6GQ6_K 18GQ8_0 22GFP16 40G| Quantization | ≈ File size | Note |
|---|---|---|
| IQ2_XXS | 5.4 GB | Extreme compression, largest quality loss |
| IQ3_XXS | 7.2 GB | Very small |
| Q3_K_M | 9.2 GB | Small |
| NVFP4 | 10 GB | NVIDIA 4-bit |
| Q4_K_S | 10.8 GB | Common |
| Q4_K_M | 11.6 GB | Most common sweet spot |
| Q5_K_M | 15.2 GB | Balanced |
| Q6_K | 18 GB | Near-lossless |
| Q8_0 | 22 GB | Near-lossless |
| FP16 | 40 GB | Original weights |
Actual files on HuggingFace
| File | Size |
|---|---|
| original/model.safetensors | 12.82 GB |
| metal/model.bin | 12.81 GB |
| model-00001-of-00002.safetensors | 4.47 GB |
| model-00000-of-00002.safetensors | 4.46 GB |
| model-00002-of-00002.safetensors | 3.88 GB |
GGUF: unsloth/gpt-oss-20b-GGUF · 564,597 downloads
| File | Size | |
|---|---|---|
| gpt-oss-20b-F16.gguf | 12.85 GB | download |
| gpt-oss-20b-Q2_K.gguf | 10.68 GB | download |
| gpt-oss-20b-Q2_K_L.gguf | 10.95 GB | download |
| gpt-oss-20b-Q3_K_M.gguf | 10.72 GB | download |
| gpt-oss-20b-Q3_K_S.gguf | 10.68 GB | download |
| gpt-oss-20b-Q4_0.gguf | 10.71 GB | download |
| gpt-oss-20b-Q4_1.gguf | 10.78 GB | download |
| gpt-oss-20b-Q4_K_M.gguf | 10.83 GB | download |
| gpt-oss-20b-Q4_K_S.gguf | 10.82 GB | download |
| gpt-oss-20b-Q5_K_M.gguf | 10.91 GB | download |
| gpt-oss-20b-Q5_K_S.gguf | 10.91 GB | download |
| gpt-oss-20b-Q6_K.gguf | 11.21 GB | download |
GGUF: lmstudio-community/gpt-oss-20b-GGUF · 117,571 downloads
| File | Size | |
|---|---|---|
| gpt-oss-20b-MXFP4.gguf | 11.28 GB | download |
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
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.