gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
qwen3:30b-a3b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 25, 2026 · Cortex-X925
Global Score
76 vs 84
Hardware Fit
46 vs 93
Quality Score
89 vs 80
Hardware
gemma4:31b qwen3:30b-a3b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M4 MaxCortex-X925
Cores1620
RAM64 GB122 GB
GPUApple M4 MaxDevice 2e12
OSmacOS 26.3.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
gemma4:31b qwen3:30b-a3b
Tokens/sec22.492.7
First chunk565 ms286 ms
TTFT30.0 s1.5 s
Load time6.9 s15.3 s
Memory usage43.9 GB20.3 GB
Memory %69%17%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
qwen3:30b-a3b
Speed
50/50
TTFT
13/20
Memory
30/30
Quality
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:30b-a3b
Reasoning
16/20
Coding
10/20
Instruction
18/20
Structured
13/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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