ministral-3:3b
OLLAMA GGUFmistral3 · 3.8B · Q4_K_M
Mar 6, 2026 · Apple M4
mistral-nemo:12b
OLLAMA GGUFllama · 12.2B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
71 vs 71
Hardware Fit
99 vs 86
Quality Score
59 vs 65
Hardware
ministral-3:3b mistral-nemo:12b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
ministral-3:3b mistral-nemo:12b
Tokens/sec42.214.6
First chunk189 msN/A
TTFT189 ms371 ms
Load time1.2 s1.0 s
Memory usage7.0 GB13.3 GB
Memory %22%42%
HW Fit Score Breakdown
ministral-3:3b
Speed
50/50
TTFT
20/20
Memory
29/30
mistral-nemo:12b
Speed
26/50
TTFT
30/20
Memory
30/30
Quality
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
mistral-nemo:12b
Reasoning
12/20
Coding
13/20
Instruction
11/20
Structured
15/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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