starcoder2:7b
starcoder2 · 7B · Q4_0
Mar 2, 2026 · Apple M4
deepseek-v2:16b
deepseek2 · 15.7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
35 vs 69
Hardware Fit
97 vs 100
Quality Score
8 vs 55
Hardware
starcoder2:7b deepseek-v2:16b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
starcoder2:7b deepseek-v2:16b
Tokens/sec23.856.6
TTFT251 ms239 ms
Load time0.4 s1.2 s
Memory usage6.3 GB17.7 GB
Memory %20%55%
HW Fit Score Breakdown
starcoder2:7b
Speed
37/40
TTFT
30/30
Memory
30/30
deepseek-v2:16b
Speed
40/40
TTFT
30/30
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
deepseek-v2:16b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
10/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong
Run yours and compare
npx metrillm@latest benchRequires Node 20+ and Ollama or LM Studio running