llama3:latest
OLLAMA GGUFllama · 8.0B · Q4_0
Mar 2, 2026 · Apple M4
microllm-250m:latest
OLLAMA GGUFllama · 256.74M · F16
Jul 5, 2026 · Apple M4 Pro
Global Score
71 vs 34
Hardware Fit
95 vs 100
Quality Score
60 vs 6
Hardware
llama3:latest microllm-250m:latest
MachineMacBook AirMac mini
CPUApple M4Apple M4 Pro
Cores1012
RAM32 GB24 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3:latest microllm-250m:latest
Tokens/sec22.3291.6
First chunkN/A50 ms
TTFT295 ms79 ms
Load time0.8 s0.0 s
Memory usage5.6 GB0.6 GB
Memory %18%2%
HW Fit Score Breakdown
llama3:latest
Speed
35/50
TTFT
30/20
Memory
30/30
microllm-250m:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
llama3:latest
Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
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
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