Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Marginal

Mar 2, 2026 · Apple M4

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score
47 vs 77
Hardware Fit
67 vs 90
Quality Score
38 vs 71

Hardware

qwen3:8b spark-x2.5-4b
MachineMacBook AirASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUApple M4AMD Ryzen 7 4800H
Cores1016
RAM32 GB15 GB
GPUApple M4AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3:8b spark-x2.5-4b
Tokens/sec18.748.9
First chunkN/A20 ms
TTFT12.1 s168 ms
Load time1.2 sN/A
Memory usage9.5 GB9.4 GB
Memory %30%61%

HW Fit Score Breakdown

qwen3:8b

Speed
31/50
TTFT
6/20
Memory
30/30

spark-x2.5-4b

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

Quality

qwen3:8b

Reasoning
5/20
Coding
5/20
Instruction
4/20
Structured
12/15
Math
2/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Poor Structured Output: Strong Math: Poor Multilingual: Strong

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
View qwen3:8b details | View spark-x2.5-4b 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