nemotron-3-nano:latest
OLLAMA GGUFnemotron_h_moe · 31.6B · Q4_K_M
Mar 13, 2026 · AMD RYZEN AI MAX+ 395
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
87 vs 91
Hardware Fit
100 vs 96
Quality Score
82 vs 89
Hardware
nemotron-3-nano:la… 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 Modeperformancebalanced
Performance
nemotron-3-nano:la… gemma4:12b-mlx
Tokens/sec59.924.7
First chunk199 ms610 ms
TTFT199 ms610 ms
Load time0.1 s3.6 s
Memory usage26.0 GB7.1 GB
Memory %21%45%
HW Fit Score Breakdown
nemotron-3-nano:latest
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
nemotron-3-nano:latest
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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