Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO GGUF

gpt-oss · 20B · MXFP4

Excellent

Nov 9, 2026 · Apple M3 Max

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
91 vs 75
Hardware Fit
90 vs 50
Quality Score
91 vs 86

Hardware

openai/gpt-oss-20b qwen2.5:72b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M3 MaxCortex-X925
Cores1620
RAM128 GB122 GB
GPUApple M3 MaxDevice 2e12
OSmacOS 27.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

openai/gpt-oss-20b qwen2.5:72b
Tokens/sec95.14.4
First chunk3 ms529 ms
TTFT2.5 s529 ms
Load time9.2 s49.7 s
Memory usage0.0 GB54.0 GB
Memory %0%44%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
10/20
Memory
30/30

qwen2.5:72b

Speed
4/50
TTFT
20/20
Memory
26/30

Quality

openai/gpt-oss-20b

Reasoning
18/20
Coding
15/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen2.5:72b

Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View openai/gpt-oss-20b details | View qwen2.5:72b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest