gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 22, 2026 · Apple M2 Max
Global Score
89 vs 95
Hardware Fit
88 vs 94
Quality Score
89 vs 96
Hardware
gemma4:12b qwen3-30b-a3b-thin…
MachineMacBook ProMac Studio
CPUApple M2 ProApple M2 Max
Cores1012
RAM16 GB96 GB
GPUApple M2 ProApple M2 Max
OSmacOS 26.5macOS 26.1
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b qwen3-30b-a3b-thin…
Tokens/sec18.580.4
First chunk752 ms46 ms
TTFT752 ms1.8 s
Load time6.1 sN/A
Memory usage7.5 GB21.2 GB
Memory %47%22%
HW Fit Score Breakdown
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
Quality
gemma4:12b
Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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