qwen3.8:latest
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
68 vs 88
Hardware Fit
22 vs 86
Quality Score
88 vs 89
Hardware
qwen3.8:latest gemma4:12b-it-qat
MachineSystem manufacturerMac mini
CPUAMD Ryzen 9 5950X 16-Core ProcessorApple M4 Pro
Cores3212
RAM32 GB24 GB
GPUNVIDIA GeForce RTX 3090Apple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.8:latest gemma4:12b-it-qat
Tokens/sec10.030.0
First chunk1041 ms686 ms
TTFT14.3 s7.1 s
Load time22.3 s5.4 s
Memory usage26.2 GB7.1 GB
Memory %82%30%
HW Fit Score Breakdown
qwen3.8:latest
Speed
12/50
TTFT
1/20
Memory
9/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
qwen3.8:latest
Reasoning
19/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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
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