Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

phi4:latest

OLLAMA GGUF

phi3 · 14.7B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
77 vs 85
Hardware Fit
90 vs 100
Quality Score
71 vs 79

Hardware

spark-x2.5-4b phi4:latest
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUAMD Ryzen 7 4800HIntel Core™ i5-14400F
Cores1616
RAM15 GB32 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

spark-x2.5-4b phi4:latest
Tokens/sec48.938.3
First chunk20 ms72 ms
TTFT168 ms72 ms
Load timeN/A6.2 s
Memory usage9.4 GB9.1 GB
Memory %61%29%

HW Fit Score Breakdown

spark-x2.5-4b

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

phi4:latest

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

phi4:latest

Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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