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

adityakale/kotakneo

OLLAMA GGUF
Good

Aug 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
96 vs 77
Hardware Fit
95 vs 100
Quality Score
96 vs 67

Hardware

qwen3-30b-a3b-thin… adityakale/kotakneo
MachineMacBook ProAZW GTR Pro
CPUApple M4 MaxAMD RYZEN AI MAX+ 395
Cores1632
RAM128 GB125 GB
GPUApple M4 MaxRadeon 8060S
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3-30b-a3b-thin… adityakale/kotakneo
Tokens/sec112.881.2
First chunk21 ms183 ms
TTFT1.5 s183 ms
Load time3.5 s2.5 s
Memory usage0.0 GB17.8 GB
Memory %0%14%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

adityakale/kotakneo

Speed
50/50
TTFT
20/20
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

adityakale/kotakneo

Reasoning
11/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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