gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
mlx-community/gemma-3-4b-it-qat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
83 vs 80
Hardware Fit
65 vs 100
Quality Score
90 vs 71
Hardware
gpt-oss:20b mlx-community/gemm…
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss:20b mlx-community/gemm…
Tokens/sec17.143.2
First chunk705 ms428 ms
TTFT10.2 s428 ms
Load time23.1 sN/A
Memory usage13.1 GB1.3 GB
Memory %55%4%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
mlx-community/gemma-3-4…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
mlx-community/gemma-3-4…
Reasoning
9/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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