gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
devstral-small-2-24b-instruct-2512
LM-STUDIO GGUFmistral3 · 24B · IQ4_XS
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
88 vs 81
Hardware Fit
86 vs 80
Quality Score
89 vs 81
Hardware
gemma4:12b-it-qat devstral-small-2-2…
MachineMac miniSystem manufacturer
CPUApple M4 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1216
RAM24 GB31 GB
GPUApple M4 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 15.6.1Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance
Performance
gemma4:12b-it-qat devstral-small-2-2…
Tokens/sec30.021.5
First chunk686 ms12 ms
TTFT7.1 s212 ms
Load time5.4 sN/A
Memory usage7.1 GB15.9 GB
Memory %30%51%
HW Fit Score Breakdown
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
devstral-small-2-24b-in…
Speed
35/50
TTFT
20/20
Memory
25/30
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
devstral-small-2-24b-in…
Reasoning
16/20
Coding
17/20
Instruction
17/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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