gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
qwen3:1.7b
OLLAMA GGUFqwen3 · 2.0B · Q4_K_M
Oct 11, 2026 · AMD Ryzen 5 5500
Global Score
88 vs 79
Hardware Fit
86 vs 100
Quality Score
89 vs 70
Hardware
gemma4:12b-it-qat qwen3:1.7b
MachineMac miniMicrosoft WSL
CPUApple M4 ProAMD Ryzen 5 5500
Cores1212
RAM24 GB8 GB
GPUApple M4 ProIntegrated / Unknown
OSmacOS 15.6.1Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown
Performance
gemma4:12b-it-qat qwen3:1.7b
Tokens/sec30.0188.0
First chunk686 ms108 ms
TTFT7.1 s1.2 s
Load time5.4 s7.5 s
Memory usage7.1 GB1.6 GB
Memory %30%21%
HW Fit Score Breakdown
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
qwen3:1.7b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:1.7b
Reasoning
16/20
Coding
7/20
Instruction
14/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate 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