Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Aug 22, 2026 · Apple M1 Pro

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score
58 vs 77
Hardware Fit
79 vs 90
Quality Score
49 vs 71

Hardware

qwen3.5:9b spark-x2.5-4b
MachineMacBook ProASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUApple M1 ProAMD Ryzen 7 4800H
Cores1016
RAM16 GB15 GB
GPUApple M1 ProAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:9b spark-x2.5-4b
Tokens/sec22.148.9
First chunk601 ms20 ms
TTFT9.1 s168 ms
Load time4.2 sN/A
Memory usage7.2 GB9.4 GB
Memory %45%61%

HW Fit Score Breakdown

qwen3.5:9b

Speed
48/50
TTFT
5/20
Memory
26/30

spark-x2.5-4b

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

Quality

qwen3.5:9b

Reasoning
15/20
Coding
4/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate 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 qwen3.5:9b 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