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

microllm-250m:latest

OLLAMA GGUF

llama · 256.74M · F16

Not Rec.

Jul 5, 2026 · Apple M4 Pro

Global Score
97 vs 34
Hardware Fit
95 vs 100
Quality Score
98 vs 6

Hardware

qwen3-30b-a3b-thin… microllm-250m:latest
MachineMac StudioMac mini
CPUApple M2 MaxApple M4 Pro
Cores1212
RAM96 GB24 GB
GPUApple M2 MaxApple M4 Pro
OSmacOS 26.1macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… microllm-250m:latest
Tokens/sec79.6291.6
First chunk11 ms50 ms
TTFT1.7 s79 ms
Load time7.1 s0.0 s
Memory usage0.0 GB0.6 GB
Memory %0%2%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

microllm-250m:latest

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

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

microllm-250m:latest

Reasoning
1/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3-30b-a3b-thin… details | View microllm-250m:latest 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