Back to leaderboard

nvidia-nemotron-3-nano-4b

LM-STUDIO GGUF

nemotron_h · 4B · Q4_K_M

Excellent

Oct 24, 2026 · Intel Core™ i3-9100F

qwen2.5:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
83 vs 77
Hardware Fit
100 vs 100
Quality Score
75 vs 67

Hardware

nvidia-nemotron-3-… qwen2.5:3b
MachineGigabyte Technology Co., Ltd. H310M S2 2.0NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i3-9100FCortex-A78AE
Cores46
RAM16 GB7 GB
GPUVirtual Desktop Monitor, NVIDIA GeForce GTX 1650Integrated / Unknown
OSМайкрософт Windows 10 Pro 10.0.19045Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

nvidia-nemotron-3-… qwen2.5:3b
Tokens/sec28.921.4
First chunk22 ms1006 ms
TTFT580 ms1.0 s
Load timeN/A6.4 s
Memory usage3.8 GB2.0 GB
Memory %24%27%

HW Fit Score Breakdown

nvidia-nemotron-3-nano-4b

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

qwen2.5:3b

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

Quality

nvidia-nemotron-3-nano-4b

Reasoning
15/20
Coding
12/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen2.5:3b

Reasoning
12/20
Coding
14/20
Instruction
11/20
Structured
15/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View nvidia-nemotron-3-… details | View qwen2.5:3b details

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