unsloth / text-generation updated 7 months ago

gpt-oss-20b-GGUF

Name: gpt-oss-20b-GGUF
Author: unsloth

See our collection for all versions of gpt-oss including GGUF, 4-bit & 16-bit formats. Learn to run gpt-oss correctly - Read our Guide. See Unsloth Dynamic 2.0 GGUFs for our quantization benchmarks. ✨ Read our gpt-oss Guide here!

Params

—

Context

131,072

Downloads 30d

560 K

Likes

760

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

Download history

daily snapshots · 10 days

560 K532 K

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
gpt-oss-20b-Q2_K.gguf	Q2_K	11.5 GB	13.1 GB	✅ Runs comfortably
gpt-oss-20b-Q3_K_S.gguf	Q3_K_S	11.5 GB	13.1 GB	✅ Runs comfortably
gpt-oss-20b-Q3_K_M.gguf	Q3_K_M	11.5 GB	13.2 GB	✅ Runs comfortably
gpt-oss-20b-Q4_0.gguf	Q4_0	11.5 GB	13.2 GB	✅ Runs comfortably
gpt-oss-20b-Q4_1.gguf	Q4_1	11.6 GB	13.2 GB	✅ Runs comfortably
gpt-oss-20b-Q4_K_M.gguf	Q4_K_M	11.6 GB	13.3 GB	✅ Runs comfortably
gpt-oss-20b-Q2_K_L.gguf	Q2_K_L	11.8 GB	13.4 GB	✅ Runs comfortably
gpt-oss-20b-F16.gguf	GGUF	13.8 GB	15.7 GB	✅ Runs comfortably

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 · Q4_0

$ ollama run gpt-oss-20b-gguf

# pin the quantization explicitly
$ ollama run gpt-oss-20b-gguf-q4_0

est. VRAM 13.2 GBon RTX 4090 · 24 GBJSON API →

Specifications

Architecture: GptOssForCausalLM
Context length: 131,072
Vocabulary: 201,088
Layers / heads: 24 / 64
Licence: apache-2.0
First seen on the Hub: 2025-08-05
Base model: gpt-oss-20b
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base gpt-oss-20b openai 8.6 M

Appears in

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