nemotron3:33b
OLLAMA GGUFnemotron_h_omni · 33.0B · Q4_K_M
Jun 28, 2026 · AMD RYZEN AI MAX+ 395
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
96 vs 84
Hardware Fit
95 vs 82
Quality Score
97 vs 85
Hardware
nemotron3:33b gemma4:12b-mlx
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M2 Pro
Cores3210
RAM125 GB16 GB
GPURadeon 8060SApple M2 Pro
OSUbuntu 24.04.4 LTSmacOS 26.5
Archx64arm64
Power Modelow-powerbalanced
Performance
nemotron3:33b gemma4:12b-mlx
Tokens/sec62.727.2
First chunk372 ms732 ms
TTFT1.0 s8.1 s
Load time13.1 s3.5 s
Memory usage24.4 GB7.1 GB
Memory %20%44%
HW Fit Score Breakdown
nemotron3:33b
Speed
50/50
TTFT
15/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
Quality
nemotron3:33b
Reasoning
19/20
Coding
18/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:12b-mlx
Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
14/15
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