starcoder2:7b
OLLAMA GGUFstarcoder2 · 7B · Q4_0
Mar 2, 2026 · Apple M4
dolphin3:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
35 vs 74
Hardware Fit
97 vs 92
Quality Score
8 vs 66
Hardware
starcoder2:7b dolphin3:8b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
starcoder2:7b dolphin3:8b
Tokens/sec23.821.0
First chunkN/A314 ms
TTFT251 ms314 ms
Load time0.4 s0.8 s
Memory usage6.3 GB10.4 GB
Memory %20%33%
HW Fit Score Breakdown
starcoder2:7b
Speed
37/50
TTFT
30/20
Memory
30/30
dolphin3:8b
Speed
42/50
TTFT
20/20
Memory
30/30
Quality
starcoder2:7b
Reasoning
0/20
Coding
1/20
Instruction
4/20
Structured
2/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
dolphin3:8b
Reasoning
12/20
Coding
13/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate 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