gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
ministral-3:3b
OLLAMA GGUFmistral3 · 3.8B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
83 vs 71
Hardware Fit
65 vs 99
Quality Score
90 vs 59
Hardware
gpt-oss:20b ministral-3:3b
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 ministral-3:3b
Tokens/sec17.142.2
First chunk705 ms189 ms
TTFT10.2 s189 ms
Load time23.1 s1.2 s
Memory usage13.1 GB7.0 GB
Memory %55%22%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
ministral-3:3b
Speed
50/50
TTFT
20/20
Memory
29/30
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
ministral-3:3b
Reasoning
5/20
Coding
16/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate 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