Back to leaderboard

nvidia/nemotron-3-nano-omni

LM-STUDIO GGUF

nemotron_h_moe · 30B · Q4_K_M

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

nemotron-3.5-lightning:latest

OLLAMA GGUF

nemotron_h_moe · 32.9B · Q4_K_M

Not Rec.

Aug 17, 2026 · Cortex-X925

Global Score
80 vs 87
Hardware Fit
81 vs 80
Quality Score
80 vs 90

Hardware

nvidia/nemotron-3-… nemotron-3.5-light…
MachineMicro-Star International Co., Ltd. MS-7E51ASUSTeK COMPUTER INC. GX10
CPUAMD Ryzen 7 9700X 8-Core ProcessorCortex-X925
Cores1620
RAM31 GB122 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsDevice 2e12
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

nvidia/nemotron-3-… nemotron-3.5-light…
Tokens/sec55.484.1
First chunk32 ms371 ms
TTFT336 ms30.0 s
Load timeN/A0.3 s
Memory usage24.3 GB24.9 GB
Memory %78%20%

HW Fit Score Breakdown

nvidia/nemotron-3-nano-…

Speed
50/50
TTFT
20/20
Memory
11/30

nemotron-3.5-lightning:…

Speed
50/50
TTFT
0/20
Memory
30/30

Quality

nvidia/nemotron-3-nano-…

Reasoning
15/20
Coding
17/20
Instruction
17/20
Structured
14/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

nemotron-3.5-lightning:…

Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
14/15
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest