qwen3.5-9b-mlx
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 12, 2026 · Apple M4 Pro
codegemma:7b
OLLAMA GGUFgemma · 9B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
77 vs 71
Hardware Fit
67 vs 91
Quality Score
81 vs 62
Hardware
qwen3.5-9b-mlx codegemma:7b
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-9b-mlx codegemma:7b
Tokens/sec20.318.7
First chunk4216 msN/A
TTFT4.2 s320 ms
Load timeN/A0.8 s
Memory usage5.6 GB8.7 GB
Memory %9%27%
HW Fit Score Breakdown
qwen3.5-9b-mlx
Speed
29/50
TTFT
8/20
Memory
30/30
codegemma:7b
Speed
31/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5-9b-mlx
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
codegemma:7b
Reasoning
1/20
Coding
14/20
Instruction
13/20
Structured
15/15
Math
10/15
Multilingual
9/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong 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