qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
76 vs 88
Hardware Fit
51 vs 86
Quality Score
87 vs 89
Hardware
qwen3-coder:latest gemma4:12b-it-qat
MachineDell Inc. Inspiron 15 3530Mac mini
CPUIntel Gen Intel® Core™ i7-1355UApple M4 Pro
Cores1212
RAM31 GB24 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M4 Pro
OScachyos rollingmacOS 15.6.1
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3-coder:latest gemma4:12b-it-qat
Tokens/sec7.630.0
First chunk2037 ms686 ms
TTFT2.0 s7.1 s
Load time8.7 s5.4 s
Memory usage18.9 GB7.1 GB
Memory %61%30%
HW Fit Score Breakdown
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
qwen3-coder:latest
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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