Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jun 25, 2026 · Cortex-X925

minimax-m2.7:cloud

OLLAMA GGUF

minimax

Not Rec.

Apr 1, 2026 · Apple M4

Global Score
92 vs 74
Hardware Fit
86 vs 34
Quality Score
95 vs 91

Hardware

gpt-oss:20b minimax-m2.7:cloud
MachineNVIDIA NVIDIA_DGX_SparkMac mini
CPUCortex-X925Apple M4
Cores2010
RAM122 GB24 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced

Performance

gpt-oss:20b minimax-m2.7:cloud
Tokens/sec60.70.0
First chunk542 ms7588 ms
TTFT3.2 s11.4 s
Load time12.0 s0.0 s
Memory usage12.0 GB0.7 GB
Memory %10%3%

HW Fit Score Breakdown

gpt-oss:20b

Speed
50/50
TTFT
6/20
Memory
30/30

minimax-m2.7:cloud

Speed
0/50
TTFT
4/20
Memory
30/30

Quality

gpt-oss:20b

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

minimax-m2.7:cloud

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gpt-oss:20b details | View minimax-m2.7:cloud 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