qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor
gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
78 vs 71
Hardware Fit
86 vs 76
Quality Score
74 vs 69
Hardware
qwen3:8b gemma4:12b-mlx
Machine—MacBook Pro
CPUAMD Ryzen 9 3900X 12-Core ProcessorApple M1 Pro
Cores2410
RAM64 GB16 GB
GPUNVIDIA GeForce RTX 4060 TiApple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3:8b gemma4:12b-mlx
Tokens/sec48.525.0
First chunk202 ms787 ms
TTFT4.3 s30.0 s
Load time4.2 s4.0 s
Memory usage5.5 GB7.1 GB
Memory %9%45%
HW Fit Score Breakdown
qwen3:8b
Speed
50/50
TTFT
6/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
Quality
qwen3:8b
Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong 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