gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
nemotron-3-nano:4b
OLLAMA GGUFnemotron_h · 4.0B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
Global Score
85 vs 95
Hardware Fit
77 vs 99
Quality Score
89 vs 93
Hardware
gemma4:26b nemotron-3-nano:4b
MachineMac miniMicrosoft WSL
CPUApple M4AMD Ryzen 5 5500
Cores1012
RAM24 GB8 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown
Performance
gemma4:26b nemotron-3-nano:4b
Tokens/sec24.5107.6
First chunk1481 ms361 ms
TTFT1.5 s1.1 s
Load time24.7 s7.9 s
Memory usage20.3 GB2.6 GB
Memory %85%34%
HW Fit Score Breakdown
gemma4:26b
Speed
49/50
TTFT
20/20
Memory
8/30
nemotron-3-nano:4b
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
gemma4:26b
Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
nemotron-3-nano:4b
Reasoning
19/20
Coding
16/20
Instruction
18/20
Structured
15/15
Math
15/15
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