Back to leaderboard

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score
61 vs 77
Hardware Fit
85 vs 90
Quality Score
51 vs 71

Hardware

qwen3:0.6b spark-x2.5-4b
MachineLENOVO 20L7CTO1WWASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUIntel Core™ i5-8350UAMD Ryzen 7 4800H
Cores816
RAM23 GB15 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSFedora Linux 43Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3:0.6b spark-x2.5-4b
Tokens/sec27.048.9
First chunk597 ms20 ms
TTFT8.7 s168 ms
Load time1.8 sN/A
Memory usage0.9 GB9.4 GB
Memory %4%61%

HW Fit Score Breakdown

qwen3:0.6b

Speed
50/50
TTFT
5/20
Memory
30/30

spark-x2.5-4b

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

Quality

qwen3:0.6b

Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate

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 qwen3:0.6b 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