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 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score
97 vs 83
Hardware Fit
95 vs 96
Quality Score
98 vs 78

Hardware

qwen3-30b-a3b-thin… google/gemma-4-e4b
MachineMac StudioASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUApple M2 MaxAMD Ryzen 9 8940HX
Cores1232
RAM96 GB15 GB
GPUApple M2 MaxNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSmacOS 26.1Microsoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… google/gemma-4-e4b
Tokens/sec79.635.9
First chunk11 ms9 ms
TTFT1.7 s182 ms
Load time7.1 sN/A
Memory usage0.0 GB6.5 GB
Memory %0%43%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

google/gemma-4-e4b

Speed
49/50
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
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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