Back to leaderboard

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 22, 2026 · Apple M2 Max

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score
95 vs 77
Hardware Fit
94 vs 90
Quality Score
96 vs 71

Hardware

qwen3-30b-a3b-thin… spark-x2.5-4b
MachineMac StudioASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUApple M2 MaxAMD Ryzen 7 4800H
Cores1216
RAM96 GB15 GB
GPUApple M2 MaxAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… spark-x2.5-4b
Tokens/sec80.448.9
First chunk46 ms20 ms
TTFT1.8 s168 ms
Load timeN/AN/A
Memory usage21.2 GB9.4 GB
Memory %22%61%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
14/20
Memory
30/30

spark-x2.5-4b

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

Quality

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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 qwen3-30b-a3b-thin… 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