gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
huihui-devstral-small-2-24b-instruct-2512-abliterated-i1
LM-STUDIO GGUFmistral3 · 24B · Q4_K_S
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
63 vs 78
Hardware Fit
62 vs 74
Quality Score
63 vs 79
Hardware
gemma4:12b huihui-devstral-sm…
MachineMacBook ProSystem manufacturer
CPUApple M1 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM16 GB32 GB
GPUApple M1 ProAMD Radeon RX 9060 XT
OSmacOS 26.6.2Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b huihui-devstral-sm…
Tokens/sec15.317.5
First chunk1142 ms20 ms
TTFT30.0 s279 ms
Load time5.4 sN/A
Memory usage7.6 GB15.6 GB
Memory %47%49%
HW Fit Score Breakdown
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
huihui-devstral-small-2…
Speed
29/50
TTFT
20/20
Memory
25/30
Quality
gemma4:12b
Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
huihui-devstral-small-2…
Reasoning
16/20
Coding
17/20
Instruction
15/20
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