ministral-3:3b
OLLAMA GGUFmistral3 · 3.8B · Q4_K_M
Mar 6, 2026 · Apple M4
lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
71 vs 80
Hardware Fit
99 vs 95
Quality Score
59 vs 73
Hardware
ministral-3:3b lfm2.5:8b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
ministral-3:3b lfm2.5:8b
Tokens/sec42.298.5
First chunk189 ms167 ms
TTFT189 ms2.5 s
Load time1.2 s3.0 s
Memory usage7.0 GB6.0 GB
Memory %22%37%
HW Fit Score Breakdown
ministral-3:3b
Speed
50/50
TTFT
20/20
Memory
29/30
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
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
lfm2.5:8b
Reasoning
2/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Strong 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