qwen2.5:0.5b
OLLAMA GGUFqwen2 · 494.03M · Q4_K_M
Mar 2, 2026 · Apple M4
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Apple M4
Global Score
57 vs 48
Hardware Fit
100 vs 77
Quality Score
39 vs 35
Hardware
qwen2.5:0.5b qwen3.5:4b
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen2.5:0.5b qwen3.5:4b
Tokens/sec165.018.9
First chunkN/A316 ms
TTFT81 ms13.0 s
Load time0.5 s3.7 s
Memory usage1.7 GB5.9 GB
Memory %5%37%
HW Fit Score Breakdown
qwen2.5:0.5b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3.5:4b
Speed
43/50
TTFT
4/20
Memory
30/30
Quality
qwen2.5:0.5b
Reasoning
6/20
Coding
6/20
Instruction
7/20
Structured
11/15
Math
5/15
Multilingual
4/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Adequate Math: Weak Multilingual: Weak
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
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