Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

gemma-3-4b-it-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

Global Score
77 vs 80
Hardware Fit
90 vs 100
Quality Score
71 vs 71

Hardware

spark-x2.5-4b gemma-3-4b-it-q4-k-m
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMMac Pro
CPUAMD Ryzen 7 4800HIntel Core™ i5-10400
Cores1612
RAM15 GB32 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUAMD Radeon RX 6700 XT
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.5.1
Archx64x64
Power Modebalancedbalanced

Performance

spark-x2.5-4b gemma-3-4b-it-q4-k-m
Tokens/sec48.975.0
First chunk20 ms136 ms
TTFT168 ms136 ms
Load timeN/A0.0 s
Memory usage9.4 GB0.8 GB
Memory %61%3%

HW Fit Score Breakdown

spark-x2.5-4b

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

gemma-3-4b-it-q4-k-m

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

gemma-3-4b-it-q4-k-m

Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View spark-x2.5-4b details | View gemma-3-4b-it-q4-k-m 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