qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
deepseek-coder:6.7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
34 vs 57
Hardware Fit
58 vs 98
Quality Score
23 vs 39
Hardware
qwen3.5:latest deepseek-coder:6.7b
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM16 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:latest deepseek-coder:6.7b
Tokens/sec13.324.1
First chunk438 msN/A
TTFT19.8 s251 ms
Load time0.2 s0.9 s
Memory usage8.0 GB12.6 GB
Memory %50%39%
HW Fit Score Breakdown
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
deepseek-coder:6.7b
Speed
38/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5:latest
Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong
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
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