hf.co/InternScience/Agents-A1-4B-Q8_0-GGUF:Q8_0
OLLAMA GGUFqwen35 · 4.21B · unknown
Aug 22, 2026 · Apple M1 Pro
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
59 vs 81
Hardware Fit
97 vs 82
Quality Score
43 vs 81
Hardware
hf.co/InternScienc… gemma4:12b-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/InternScienc… gemma4:12b-mlx
Tokens/sec30.925.3
First chunk891 ms761 ms
TTFT891 ms7.7 s
Load time3.6 s3.6 s
Memory usage6.6 GB7.1 GB
Memory %41%44%
HW Fit Score Breakdown
hf.co/InternScience/Age…
Speed
50/50
TTFT
20/20
Memory
27/30
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
Quality
hf.co/InternScience/Age…
Reasoning
13/20
Coding
15/20
Instruction
2/20
Structured
0/15
Math
13/15
Multilingual
0/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
gemma4:12b-mlx
Reasoning
16/20
Coding
15/20
Instruction
12/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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