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 22, 2026 · Apple M2 Max

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

Global Score
95 vs 61
Hardware Fit
94 vs 69
Quality Score
96 vs 58

Hardware

qwen3-30b-a3b-thin… qwen3.5:4b
MachineMac StudioGigabyte Technology Co., Ltd. H170M-D3H
CPUApple M2 MaxIntel Core™ i5-6500
Cores124
RAM96 GB16 GB
GPUApple M2 MaxGP104 [GeForce GTX 1070]
OSmacOS 26.1Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3-30b-a3b-thin… qwen3.5:4b
Tokens/sec80.435.7
First chunk46 ms438 ms
TTFT1.8 s5.1 s
Load timeN/A40.1 s
Memory usage21.2 GB5.5 GB
Memory %22%35%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
14/20
Memory
30/30

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

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

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
View qwen3-30b-a3b-thin… details | View qwen3.5:4b 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