gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
qwen3.6-27b-mtp-pi-reasoning
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
89 vs 85
Hardware Fit
88 vs 80
Quality Score
89 vs 87
Hardware
gemma4:12b qwen3.6-27b-mtp-pi…
MachineMacBook ProASUS
CPUApple M2 ProAMD Ryzen 7 7800X3D 8-Core Processor
Cores1016
RAM16 GB31 GB
GPUApple M2 ProNVIDIA GeForce RTX 4090, Raphael
OSmacOS 26.5cachyos rolling
Archarm64x64
Power Modebalancedperformance
Performance
gemma4:12b qwen3.6-27b-mtp-pi…
Tokens/sec18.438.8
First chunk758 ms17 ms
TTFT758 ms432 ms
Load time0.3 sN/A
Memory usage7.5 GB24.6 GB
Memory %47%81%
HW Fit Score Breakdown
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
qwen3.6-27b-mtp-pi-reas…
Speed
50/50
TTFT
20/20
Memory
10/30
Quality
gemma4:12b
Reasoning
17/20
Coding
18/20
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
qwen3.6-27b-mtp-pi-reas…
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
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