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

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score
97 vs 84
Hardware Fit
95 vs 94
Quality Score
98 vs 80

Hardware

qwen3-30b-a3b-thin… qwen3.5:9b
MachineMac StudioASUS
CPUApple M2 MaxIntel Core™ i5-14600KF
Cores1220
RAM96 GB32 GB
GPUApple M2 MaxNVIDIA GeForce RTX 4070 Ti SUPER
OSmacOS 26.1Microsoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… qwen3.5:9b
Tokens/sec79.686.3
First chunk11 ms316 ms
TTFT1.7 s316 ms
Load time7.1 s0.3 s
Memory usage0.0 GB8.1 GB
Memory %0%25%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

qwen3.5:9b

Speed
50/50
TTFT
20/20
Memory
24/30

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

qwen3.5:9b

Reasoning
14/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-30b-a3b-thin… details | View qwen3.5:9b 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