Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

qwen3-vl:30b

OLLAMA GGUF

qwen3vlmoe · 31.1B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

Global Score
77 vs 80
Hardware Fit
90 vs 98
Quality Score
71 vs 72

Hardware

spark-x2.5-4b qwen3-vl:30b
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMASUS
CPUAMD Ryzen 7 4800HIntel Core™ Ultra 9 285K
Cores1624
RAM15 GB47 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 5090, Intel(R) Graphics
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

spark-x2.5-4b qwen3-vl:30b
Tokens/sec48.9208.9
First chunk20 ms102 ms
TTFT168 ms684 ms
Load timeN/A0.1 s
Memory usage9.4 GB22.0 GB
Memory %61%47%

HW Fit Score Breakdown

spark-x2.5-4b

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

qwen3-vl:30b

Speed
50/50
TTFT
20/20
Memory
28/30

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

qwen3-vl:30b

Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View spark-x2.5-4b details | View qwen3-vl:30b 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