Back to leaderboard

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

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Aug 20, 2026 · Apple M4 Max

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor

Global Score
96 vs 78
Hardware Fit
95 vs 86
Quality Score
96 vs 74

Hardware

qwen3-30b-a3b-thin… qwen3:8b
MachineMacBook Pro—
CPUApple M4 MaxAMD Ryzen 9 3900X 12-Core Processor
Cores1624
RAM128 GB64 GB
GPUApple M4 MaxNVIDIA GeForce RTX 4060 Ti
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… qwen3:8b
Tokens/sec112.848.5
First chunk21 ms202 ms
TTFT1.5 s4.3 s
Load time3.5 s4.2 s
Memory usage0.0 GB5.5 GB
Memory %0%9%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

qwen3:8b

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

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

qwen3:8b

Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-30b-a3b-thin… details | View qwen3:8b 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