qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
84 vs 81
Hardware Fit
97 vs 82
Quality Score
79 vs 81
Hardware
qwen3:8b gemma4:12b-mlx
MachineASUSMacBook Pro
CPUIntel Core™ Ultra 9 285KApple M2 Pro
Cores2410
RAM47 GB16 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsApple M2 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.5
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3:8b gemma4:12b-mlx
Tokens/sec208.025.3
First chunk82 ms761 ms
TTFT1.3 s7.7 s
Load time1.5 s3.6 s
Memory usage9.6 GB7.1 GB
Memory %20%44%
HW Fit Score Breakdown
qwen3:8b
Speed
50/50
TTFT
18/20
Memory
29/30
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
Quality
qwen3:8b
Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:12b-mlx
Reasoning
16/20
Coding
15/20
Instruction
12/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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