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

vicuna:13b

OLLAMA GGUF

llama · 13B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

Global Score
95 vs 59
Hardware Fit
94 vs 84
Quality Score
96 vs 48

Hardware

qwen3-30b-a3b-thin… vicuna:13b
MachineMac StudioMacBook Air
CPUApple M2 MaxApple M4
Cores1210
RAM96 GB32 GB
GPUApple M2 MaxApple M4
OSmacOS 26.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… vicuna:13b
Tokens/sec80.413.4
First chunk46 msN/A
TTFT1.8 s438 ms
Load timeN/A0.6 s
Memory usage21.2 GB10.3 GB
Memory %22%32%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

vicuna:13b

Speed
24/50
TTFT
30/20
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

vicuna:13b

Reasoning
7/20
Coding
5/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3-30b-a3b-thin… details | View vicuna:13b 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