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

Ling-3.0-tiny-IQ4_XS:latest

OLLAMA GGUF

bailingmoe3 · 7.9B · IQ4_XS

Excellent

Aug 30, 2026 · Intel Core™ i7-7700HQ

Global Score
96 vs 87
Hardware Fit
95 vs 100
Quality Score
96 vs 82

Hardware

qwen3-30b-a3b-thin… Ling-3.0-tiny-IQ4_…
MachineMacBook ProASUSTeK COMPUTER INC. GL702VMK
CPUApple M4 MaxIntel Core™ i7-7700HQ
Cores168
RAM128 GB16 GB
GPUApple M4 MaxNVIDIA GeForce GTX 1060
OSmacOS 26.5.2Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… Ling-3.0-tiny-IQ4_…
Tokens/sec112.824.7
First chunk21 ms283 ms
TTFT1.5 s283 ms
Load time3.5 s45.8 s
Memory usage0.0 GB4.3 GB
Memory %0%27%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

Ling-3.0-tiny-IQ4_XS:la…

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

Ling-3.0-tiny-IQ4_XS:la…

Reasoning
17/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
9/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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