Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score
53 vs 77
Hardware Fit
81 vs 90
Quality Score
41 vs 71

Hardware

qwen3.5:4b-mlx spark-x2.5-4b
MachineMac miniASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUApple M2AMD Ryzen 7 4800H
Cores816
RAM8 GB15 GB
GPUApple M2AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx spark-x2.5-4b
Tokens/sec24.848.9
First chunk317 ms20 ms
TTFT7.4 s168 ms
Load time0.0 sN/A
Memory usage3.9 GB9.4 GB
Memory %49%61%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
25/30

spark-x2.5-4b

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

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor 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 qwen3.5:4b-mlx 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