Back to leaderboard

qwen2.5-coder:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score
73 vs 77
Hardware Fit
100 vs 90
Quality Score
61 vs 71

Hardware

qwen2.5-coder:3b spark-x2.5-4b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUCortex-A78AEAMD Ryzen 7 4800H
Cores616
RAM7 GB15 GB
GPUIntegrated / UnknownAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen2.5-coder:3b spark-x2.5-4b
Tokens/sec21.348.9
First chunk969 ms20 ms
TTFT969 ms168 ms
Load time6.6 sN/A
Memory usage2.0 GB9.4 GB
Memory %27%61%

HW Fit Score Breakdown

qwen2.5-coder:3b

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

spark-x2.5-4b

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

Quality

qwen2.5-coder:3b

Reasoning
8/20
Coding
15/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

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
View qwen2.5-coder:3b details | View spark-x2.5-4b 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