mlx-community/quantized-gemma-2b-it
LM-STUDIO GGUFMar 5, 2026 · Apple M4
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Apr 1, 2026 · Apple M4
Global Score
45 vs 87
Hardware Fit
100 vs 83
Quality Score
21 vs 88
Hardware
mlx-community/quan… gpt-oss:20b
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/quan… gpt-oss:20b
Tokens/sec44.424.3
First chunk336 ms529 ms
TTFT336 ms4.5 s
Load timeN/A11.2 s
Memory usage0.1 GB13.1 GB
Memory %0%55%
HW Fit Score Breakdown
mlx-community/quantized…
Speed
50/50
TTFT
20/20
Memory
30/30
gpt-oss:20b
Speed
49/50
TTFT
11/20
Memory
23/30
Quality
mlx-community/quantized…
Reasoning
4/20
Coding
1/20
Instruction
9/20
Structured
4/15
Math
2/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Poor
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
11/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest