qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 7, 2026 · AMD Ryzen 5 5500
gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
71 vs 71
Hardware Fit
56 vs 76
Quality Score
78 vs 69
Hardware
qwen3.5:9b gemma4:12b-mlx
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 5 5500Apple M1 Pro
Cores1210
RAM16 GB16 GB
GPUNVIDIA GeForce RTX 3060Apple M1 Pro
OSMicrosoft Windows 11 IoT Enterprise LTSC 10.0.26100macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.5:9b gemma4:12b-mlx
Tokens/sec5.325.0
First chunk1624 ms787 ms
TTFT1.6 s30.0 s
Load time4.0 s4.0 s
Memory usage7.9 GB7.1 GB
Memory %50%45%
HW Fit Score Breakdown
qwen3.5:9b
Speed
11/50
TTFT
20/20
Memory
25/30
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
Quality
qwen3.5:9b
Reasoning
14/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
gemma4:12b-mlx
Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak 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