qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Apple M4
Global Score
34 vs 48
Hardware Fit
58 vs 77
Quality Score
23 vs 35
Hardware
qwen3.5:latest qwen3.5:4b
MachineMac miniMac mini
CPUApple M4Apple M4
Cores1010
RAM16 GB16 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:latest qwen3.5:4b
Tokens/sec13.318.9
First chunk438 ms316 ms
TTFT19.8 s13.0 s
Load time0.2 s3.7 s
Memory usage8.0 GB5.9 GB
Memory %50%37%
HW Fit Score Breakdown
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
qwen3.5:4b
Speed
43/50
TTFT
4/20
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
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