spark-x2.5-4b

spark2_5 · 4B · Q4_K_M

ASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM (AMD Ryzen 7 4800H)

15 GB · Microsoft Windows 11 Pro 10.0.26200

Tested on September 30, 2026

Top 49% Compare

Global Score

77 /100

Good

Hardware Fit

90/100

Quality

71/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: ASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPU: AMD Ryzen 7 4800H
Cores: 16 total (16 perf)
Frequency: 2.9 GHz
RAM: 15 GB DDR4
GPU: AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OS: Microsoft Windows 11 Pro 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 48.9
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.8
First chunk latency Delay before the first streamed chunk arrives from runtime: 20 ms
Time to first token How fast the model starts responding — lower is better: 168 ms
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 9.4 GB (61%)
Total tokens Total number of tokens generated across all benchmark prompts: 1334

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

20/30

Quality

Reasoning

13/20

Coding

14/20

Instruction following

16/20

Structured output

15/15

Math

4/15

Multilingual

9/10

Category levels

Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: LM Studio
Model format: GGUF
Hardware profile: BALANCED
Result hash: 32d59bc321a7efae2301944065587f0f7c7abfcc15dc7d805e2a06a0c22a0d3b

Interpretation

Hardware fit: 90/100. Overall suitability: GOOD (Global 77/100). Category profile: Reasoning: Adequate, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.

Bench Environment

Power: AC CPU load: avg 51% (peak 62%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest