Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

mlx-community/Nanbeige4.1-3B-8bit

LM-STUDIO GGUF
Marginal

Mar 5, 2026 · Apple M4

Global Score
93 vs 53
Hardware Fit
85 vs 99
Quality Score
96 vs 33

Hardware

gpt-oss:20b mlx-community/Nanb…
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPUAMD Radeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced

Performance

gpt-oss:20b mlx-community/Nanb…
Tokens/sec47.125.4
First chunk320 ms266 ms
TTFT1.8 s266 ms
Load time3.8 sN/A
Memory usage16.4 GB0.0 GB
Memory %13%0%

HW Fit Score Breakdown

gpt-oss:20b

Speed
44/50
TTFT
11/20
Memory
30/30

mlx-community/Nanbeige4…

Speed
49/50
TTFT
20/20
Memory
30/30

Quality

gpt-oss:20b

Reasoning
19/20
Coding
19/20
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

mlx-community/Nanbeige4…

Reasoning
10/20
Coding
7/20
Instruction
1/20
Structured
1/15
Math
11/15
Multilingual
3/10
Reasoning: Adequate Coding: Weak Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Weak

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