qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Apple M4
mlx-community/stablelm-2-zephyr-1_6b-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
48 vs 50
Hardware Fit
77 vs 100
Quality Score
35 vs 29
Hardware
qwen3.5:4b mlx-community/stab…
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 mlx-community/stab…
Tokens/sec18.993.6
First chunk316 ms166 ms
TTFT13.0 s166 ms
Load time3.7 sN/A
Memory usage5.9 GB0.7 GB
Memory %37%2%
HW Fit Score Breakdown
qwen3.5:4b
Speed
43/50
TTFT
4/20
Memory
30/30
mlx-community/stablelm-…
Speed
50/50
TTFT
20/20
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
mlx-community/stablelm-…
Reasoning
7/20
Coding
2/20
Instruction
9/20
Structured
3/15
Math
4/15
Multilingual
4/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Poor 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