Back to leaderboard

microllm-50m:latest

OLLAMA GGUF

llama · 49.31M · F16

Not Rec.

Jun 28, 2026 · Apple M4 Pro

qwen/qwen3-30b-a3b-2507

LM-STUDIO MLX

qwen3_moe · 30B · 4bit

Excellent

Mar 4, 2026 · Apple M4

Global Score
28 vs 94
Hardware Fit
80 vs 100
Quality Score
5 vs 91

Hardware

microllm-50m:latest qwen/qwen3-30b-a3b…
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1210
RAM24 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

microllm-50m:latest qwen/qwen3-30b-a3b…
Tokens/sec1000000.044.8
First chunk50 ms405 ms
TTFT30.0 s405 ms
Load time0.3 sN/A
Memory usage0.1 GB16.0 GB
Memory %1%50%

HW Fit Score Breakdown

microllm-50m:latest

Speed
50/50
TTFT
0/20
Memory
30/30

qwen/qwen3-30b-a3b-2507

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

Quality

microllm-50m:latest

Reasoning
0/20
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

qwen/qwen3-30b-a3b-2507

Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View microllm-50m:latest details | View qwen/qwen3-30b-a3b… 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