gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
81 vs 46
Hardware Fit
82 vs 61
Quality Score
81 vs 40
Hardware
gemma4:12b-mlx llama3.1:8b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M2 ProCortex-A78AE
Cores106
RAM16 GB7 GB
GPUApple M2 ProIntegrated / Unknown
OSmacOS 26.5Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx llama3.1:8b
Tokens/sec25.37.8
First chunk761 ms1625 ms
TTFT7.7 s1.6 s
Load time3.6 s21.8 s
Memory usage7.1 GB5.2 GB
Memory %44%71%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
Quality
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
llama3.1:8b
Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak 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