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-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
97 vs 83
Hardware Fit
95 vs 96
Quality Score
98 vs 78

Hardware

qwen3-30b-a3b-thin… qwen3-vl:4b-instruct
MachineMac StudioMac Studio
CPUApple M2 MaxApple M2 Max
Cores1212
RAM96 GB96 GB
GPUApple M2 MaxApple M2 Max
OSmacOS 26.1macOS 26.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… qwen3-vl:4b-instruct
Tokens/sec79.691.2
First chunk11 ms150 ms
TTFT1.7 s150 ms
Load time7.1 s5.3 s
Memory usage0.0 GB42.5 GB
Memory %0%44%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

qwen3-vl:4b-instruct

Speed
50/50
TTFT
20/20
Memory
26/30

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-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-30b-a3b-thin… details | View qwen3-vl:4b-instruct 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