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 20, 2026 · Apple M2 Max

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
97 vs 68
Hardware Fit
95 vs 93
Quality Score
98 vs 57

Hardware

qwen3-30b-a3b-thin… google/gemma-4-e4b
MachineMac StudioLENOVO 82JQ
CPUApple M2 MaxAMD Ryzen 7 5800H
Cores1216
RAM96 GB16 GB
GPUApple M2 MaxNVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 26.1Microsoft Windows 11 家庭版 中文版 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… google/gemma-4-e4b
Tokens/sec79.626.2
First chunk11 ms17 ms
TTFT1.7 s572 ms
Load time7.1 sN/A
Memory usage0.0 GB6.5 GB
Memory %0%41%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
15/20
Memory
30/30

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

Quality

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor
View qwen3-30b-a3b-thin… details | View google/gemma-4-e4b 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