deepseek-coder:6.7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 2, 2026 · Apple M4
qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
Global Score
57 vs 58
Hardware Fit
98 vs 82
Quality Score
39 vs 48
Hardware
deepseek-coder:6.7b qwen3:14b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Max
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M1 Max
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
deepseek-coder:6.7b qwen3:14b
Tokens/sec24.124.4
First chunkN/A294 ms
TTFT251 ms7.9 s
Load time0.9 s3.7 s
Memory usage12.6 GB13.8 GB
Memory %39%43%
HW Fit Score Breakdown
deepseek-coder:6.7b
Speed
38/50
TTFT
30/20
Memory
30/30
qwen3:14b
Speed
47/50
TTFT
5/20
Memory
30/30
Quality
deepseek-coder:6.7b
Reasoning
4/20
Coding
14/20
Instruction
9/20
Structured
6/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Adequate Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
qwen3:14b
Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor 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