Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

qwen/qwen3-coder-30b

LM-STUDIO GGUF

qwen3moe · 30B · Q4_K_M

Excellent

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
77 vs 88
Hardware Fit
90 vs 84
Quality Score
71 vs 89

Hardware

spark-x2.5-4b qwen/qwen3-coder-30b
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMASUS
CPUAMD Ryzen 7 4800HAMD Ryzen 7 7800X3D 8-Core Processor
Cores1616
RAM15 GB31 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 11 Pro 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedperformance

Performance

spark-x2.5-4b qwen/qwen3-coder-30b
Tokens/sec48.995.4
First chunk20 ms11 ms
TTFT168 ms179 ms
Load timeN/AN/A
Memory usage9.4 GB22.2 GB
Memory %61%73%

HW Fit Score Breakdown

spark-x2.5-4b

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

qwen/qwen3-coder-30b

Speed
50/50
TTFT
20/20
Memory
14/30

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

qwen/qwen3-coder-30b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View spark-x2.5-4b details | View qwen/qwen3-coder-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