Models

Loading community benchmarks…

← All models

Community benchmarks

GPT OSS 20B

Submitted benchmarks for GPT OSS 20B. Browse individual runs and their measurement settings, or open the report JSON for full benchmark details.

Compare chips Compare runtimes Add your benchmark

Submitted runs: 36
Chips tested: 11
Contributors: 3

Model identity

Grouped as openai/gpt-oss-20b. The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.. Artifact verification confirms published model bytes, not that a community-submitted benchmark was honestly executed. Hover or tap a label for what it means.

This model group collects runs reported as basecompute/gpt-oss-20b, Gpt-Oss-20B, gpt-oss-20b-MXFP4, gpt-oss-20b-Q4, gpt-oss-20b-Q8. Individual results keep the package name and format they were submitted with.

View on Hugging Face ↗

Published files benchmarked

basecompute/gpt-oss-20b/gpt-oss-20b-Q4.base (opens in a new tab)BaseRTQ4· 11 runs
basecompute/gpt-oss-20b/gpt-oss-20b-MXFP4.base (opens in a new tab)BaseRTmxfp4· 9 runs
basecompute/gpt-oss-20b/gpt-oss-20b-Q8.base (opens in a new tab)BaseRTQ8· 9 runs
unsloth/gpt-oss-20b-GGUF/gpt-oss-20b-F16.gguf

Benchmark results

Peak throughput is the highest reported value and may come from different runs. Compare model, quantisation, backend, and token counts before drawing conclusions. Model verification identifies published artifact bytes; community benchmark execution is not remotely attested.

Individual runs for GPT OSS 20B. Throughput is in tokens per second; dates use your browser timezone. Hover a date for the exact local time.
Model / runtime / format	Chip / backend	Decode	Prefill	Peak process memory	Contributor

Gpt-Oss-20B llama.cppF16 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT (RADV NAVI31) Vulkan	146.8 tok/s TG128	3,262 tok/s PP512	13,324.5 MiB	arki05	11 Sep 2026	View Benchmark
Gpt-Oss-20B llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT (RADV NAVI31) Vulkan	195.6 tok/s TG128	3,292 tok/s PP512	11,257.0 MiB	arki05	11 Sep 2026	View Benchmark
Gpt-Oss-20B llama.cppF16 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT ROCm	128.8 tok/s TG128	3,604 tok/s PP512	15,074.1 MiB	arki05	11 Sep 2026	View Benchmark
Gpt-Oss-20B llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT ROCm	160.1 tok/s TG128	3,502 tok/s PP512	13,008.5 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/gpt-oss-20b BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro Metal	110.1 tok/s TG128	1,156 tok/s PP512	7,882.1 MiB	arki05	11 Sep 2026	View Benchmark
Gpt-Oss-20B llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro BLAS + Metal	96.3 tok/s TG128	1,849 tok/s PP512	11,709.7 MiB	arki05	11 Sep 2026	View Benchmark
Gpt-Oss-20B llama.cppF16 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro BLAS + Metal	66.6 tok/s TG128	1,852 tok/s PP512	13,776.5 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/gpt-oss-20b BaseRTmxfp4· default-bf16 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro Metal	103.6 tok/s TG128	1,013 tok/s PP512	10,492.4 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/gpt-oss-20b BaseRTQ8· default-q8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro Metal	100.6 tok/s TG128	1,065 tok/s PP512	8,240.3 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/gpt-oss-20b BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro Metal	110.9 tok/s TG128	1,155 tok/s PP512	7,888.4 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/gpt-oss-20b BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Max Metal	169.0 tok/s TG128	2,179 tok/s PP512	7,882.2 MiB	lukas	11 Sep 2026	View Benchmark