microllm-250m:latest
OLLAMA GGUFllama · 256.74M · F16
Jul 5, 2026 · Apple M4 Pro
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
34 vs 72
Hardware Fit
100 vs 71
Quality Score
6 vs 72
Hardware
microllm-250m:latest ministral-3:8b
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1210
RAM24 GB16 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 26.5.2macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
microllm-250m:latest ministral-3:8b
Tokens/sec291.619.8
First chunk50 ms269 ms
TTFT79 ms269 ms
Load time0.0 s10.7 s
Memory usage0.6 GB13.7 GB
Memory %2%86%
HW Fit Score Breakdown
microllm-250m:latest
Speed
50/50
TTFT
20/20
Memory
30/30
ministral-3:8b
Speed
44/50
TTFT
20/20
Memory
7/30
Quality
microllm-250m:latest
Reasoning
1/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate 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