starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Mar 2, 2026 · Apple M4
microllm-10m:latest
OLLAMA GGUFllama · 10.00M · F16
Jun 28, 2026 · Apple M4 Pro
Global Score
39 vs 33
Hardware Fit
100 vs 100
Quality Score
13 vs 4
Hardware
starcoder2:3b microllm-10m:latest
MachineMacBook AirMac mini
CPUApple M4Apple M4 Pro
Cores1012
RAM32 GB24 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
starcoder2:3b microllm-10m:latest
Tokens/sec49.41544.8
First chunkN/A12 ms
TTFT155 ms12 ms
Load time0.4 s0.0 s
Memory usage3.0 GB0.0 GB
Memory %9%0%
HW Fit Score Breakdown
starcoder2:3b
Speed
40/50
TTFT
30/20
Memory
30/30
microllm-10m:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
starcoder2:3b
Reasoning
0/20
Coding
2/20
Instruction
5/20
Structured
2/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
microllm-10m:latest
Reasoning
0/20
Coding
0/20
Instruction
4/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor 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