gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex-mtp
LM-STUDIO GGUFqwen35moe · 35B
Jun 19, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
91 vs 92
Hardware Fit
96 vs 87
Quality Score
89 vs 94
Hardware
gemma4:12b-mlx qwen3.6-35b-a3b-cl…
MachineMacBook ProGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M2 ProAMD Ryzen 5 5600X 6-Core Processor
Cores1012
RAM16 GB47 GB
GPUApple M2 ProAD106 [GeForce RTX 4060 Ti]
OSmacOS 26.5cachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
gemma4:12b-mlx qwen3.6-35b-a3b-cl…
Tokens/sec24.742.6
First chunk610 ms13 ms
TTFT610 ms3.1 s
Load time3.6 sN/A
Memory usage7.1 GB23.2 GB
Memory %45%49%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
qwen3.6-35b-a3b-claude-…
Speed
50/50
TTFT
12/20
Memory
25/30
Quality
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.6-35b-a3b-claude-…
Reasoning
20/20
Coding
16/20
Instruction
19/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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