qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 5, 2026 · Apple M1 Max
deepseek-coder:6.7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
62 vs 57
Hardware Fit
100 vs 98
Quality Score
46 vs 39
Hardware
qwen3.5:0.8b deepseek-coder:6.7b
MachineMacBook ProMacBook Air
CPUApple M1 MaxApple M4
Cores1010
RAM32 GB32 GB
GPUApple M1 MaxApple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:0.8b deepseek-coder:6.7b
Tokens/sec65.824.1
First chunk230 msN/A
TTFT230 ms251 ms
Load time1.5 s0.9 s
Memory usage2.6 GB12.6 GB
Memory %8%39%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
50/50
TTFT
20/20
Memory
30/30
deepseek-coder:6.7b
Speed
38/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5:0.8b
Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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