qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Apple M4
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
48 vs 47
Hardware Fit
77 vs 67
Quality Score
35 vs 38
Hardware
qwen3.5:4b qwen3:8b
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM16 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:4b qwen3:8b
Tokens/sec18.918.7
First chunk316 msN/A
TTFT13.0 s12.1 s
Load time3.7 s1.2 s
Memory usage5.9 GB9.5 GB
Memory %37%30%
HW Fit Score Breakdown
qwen3.5:4b
Speed
43/50
TTFT
4/20
Memory
30/30
qwen3:8b
Speed
31/50
TTFT
6/20
Memory
30/30
Quality
qwen3.5:4b
Reasoning
10/20
Coding
1/20
Instruction
4/20
Structured
3/15
Math
8/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Strong
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