qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 5, 2026 · Apple M1 Max
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
62 vs 47
Hardware Fit
100 vs 67
Quality Score
46 vs 38
Hardware
qwen3.5:0.8b qwen3:8b
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 qwen3:8b
Tokens/sec65.818.7
First chunk230 msN/A
TTFT230 ms12.1 s
Load time1.5 s1.2 s
Memory usage2.6 GB9.5 GB
Memory %8%30%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3:8b
Speed
31/50
TTFT
6/20
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
qwen3:8b
Reasoning
5/20
Coding
5/20
Instruction
4/20
Structured
12/15
Math
2/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Poor Structured Output: Strong 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