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

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

Global Score
96 vs 81
Hardware Fit
95 vs 98
Quality Score
96 vs 74

Hardware

qwen3-30b-a3b-thin… qwen3.5:4b
MachineMacBook ProMicrosoft WSL
CPUApple M4 MaxAMD Ryzen 5 5500
Cores1612
RAM128 GB8 GB
GPUApple M4 MaxIntegrated / Unknown
OSmacOS 26.5.2Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown

Performance

qwen3-30b-a3b-thin… qwen3.5:4b
Tokens/sec112.893.7
First chunk21 ms249 ms
TTFT1.5 s249 ms
Load time3.5 s10.1 s
Memory usage0.0 GB2.9 GB
Memory %0%38%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

qwen3.5:4b

Speed
50/50
TTFT
20/20
Memory
28/30

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
15/20
Coding
13/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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