hf.co/bartowski/ai9stars_G9v3-3B-GGUF:BF16
OLLAMA GGUFllama · 2.99B · BF16
Aug 23, 2026 · Apple M1 Pro
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
64 vs 78
Hardware Fit
92 vs 72
Quality Score
52 vs 81
Hardware
hf.co/bartowski/ai… gemma4:e4b-mlx
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M2 Pro
Cores1010
RAM16 GB16 GB
GPUApple M1 ProApple M2 Pro
OSmacOS 26.6.2macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/bartowski/ai… gemma4:e4b-mlx
Tokens/sec29.926.9
First chunk100 ms222 ms
TTFT100 ms222 ms
Load time3.4 s0.1 s
Memory usage8.9 GB15.4 GB
Memory %56%96%
HW Fit Score Breakdown
hf.co/bartowski/ai9star…
Speed
50/50
TTFT
20/20
Memory
22/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
2/30
Quality
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
gemma4:e4b-mlx
Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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