gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
hf.co/bartowski/ai9stars_G9v3-3B-GGUF:BF16
OLLAMA GGUFllama · 2.99B · BF16
Aug 23, 2026 · Apple M1 Pro
Global Score
76 vs 64
Hardware Fit
46 vs 92
Quality Score
89 vs 52
Hardware
gemma4:31b hf.co/bartowski/ai…
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M1 Pro
Cores1610
RAM64 GB16 GB
GPUApple M4 MaxApple M1 Pro
OSmacOS 26.3.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:31b hf.co/bartowski/ai…
Tokens/sec22.429.9
First chunk565 ms100 ms
TTFT30.0 s100 ms
Load time6.9 s3.4 s
Memory usage43.9 GB8.9 GB
Memory %69%56%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
hf.co/bartowski/ai9star…
Speed
50/50
TTFT
20/20
Memory
22/30
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
hf.co/bartowski/ai9star…
Reasoning
17/20
Coding
14/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
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