Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Not Rec.

Sep 29, 2026 · Apple M5 Max

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
83 vs 78
Hardware Fit
80 vs 59
Quality Score
84 vs 86

Hardware

openai/gpt-oss-20b qwen2.5-coder:32b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M5 MaxCortex-X925
Cores1820
RAM128 GB122 GB
GPUApple M5 MaxDevice 2e12
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

openai/gpt-oss-20b qwen2.5-coder:32b
Tokens/sec138.49.5
First chunk3 ms394 ms
TTFT30.0 s395 ms
Load time6.8 s72.1 s
Memory usage0.5 GB26.5 GB
Memory %0%22%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
0/20
Memory
30/30

qwen2.5-coder:32b

Speed
9/50
TTFT
20/20
Memory
30/30

Quality

openai/gpt-oss-20b

Reasoning
18/20
Coding
12/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen2.5-coder:32b

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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