qwen3.5-9b-mlx
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 11, 2026 · Apple M4
gemma3:12b
OLLAMA GGUFgemma3 · 12.2B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
59 vs 80
Hardware Fit
65 vs 83
Quality Score
57 vs 78
Hardware
qwen3.5-9b-mlx gemma3:12b
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-9b-mlx gemma3:12b
Tokens/sec14.312.7
First chunk24 msN/A
TTFT13.4 s560 ms
Load time13.3 s2.8 s
Memory usage2.5 GB11.0 GB
Memory %10%34%
HW Fit Score Breakdown
qwen3.5-9b-mlx
Speed
32/50
TTFT
3/20
Memory
30/30
gemma3:12b
Speed
23/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5-9b-mlx
Reasoning
10/20
Coding
17/20
Instruction
5/20
Structured
9/15
Math
11/15
Multilingual
5/10
Reasoning: Weak Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Adequate
gemma3:12b
Reasoning
14/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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