Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

nvidia-nemotron-3-nano-4b

LM-STUDIO GGUF

nemotron_h · 4B · Q4_K_M

Excellent

Oct 24, 2026 · Intel Core™ i3-9100F

Global Score
77 vs 83
Hardware Fit
90 vs 100
Quality Score
71 vs 75

Hardware

spark-x2.5-4b nvidia-nemotron-3-…
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMGigabyte Technology Co., Ltd. H310M S2 2.0
CPUAMD Ryzen 7 4800HIntel Core™ i3-9100F
Cores164
RAM15 GB16 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUVirtual Desktop Monitor, NVIDIA GeForce GTX 1650
OSMicrosoft Windows 11 Pro 10.0.26200Майкрософт Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

spark-x2.5-4b nvidia-nemotron-3-…
Tokens/sec48.928.9
First chunk20 ms22 ms
TTFT168 ms580 ms
Load timeN/AN/A
Memory usage9.4 GB3.8 GB
Memory %61%24%

HW Fit Score Breakdown

spark-x2.5-4b

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

nvidia-nemotron-3-nano-4b

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

Quality

spark-x2.5-4b

Reasoning
13/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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

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