gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
deepseek-r1-distill-qwen-14b-mlx
LM-STUDIO MLXqwen2 · 14B · 5bit
Mar 11, 2026 · Apple M4
Global Score
88 vs 36
Hardware Fit
86 vs 53
Quality Score
89 vs 28
Hardware
gemma4:12b-it-qat deepseek-r1-distil…
MachineMac miniMac mini
CPUApple M4 ProApple M4
Cores1210
RAM24 GB24 GB
GPUApple M4 ProApple M4
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b-it-qat deepseek-r1-distil…
Tokens/sec30.010.3
First chunk686 ms27 ms
TTFT7.1 s20.7 s
Load time5.4 s15.4 s
Memory usage7.1 GB1.0 GB
Memory %30%4%
HW Fit Score Breakdown
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
deepseek-r1-distill-qwe…
Speed
23/50
TTFT
0/20
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
deepseek-r1-distill-qwe…
Reasoning
3/20
Coding
6/20
Instruction
6/20
Structured
3/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Poor 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