Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

microllm-250m:latest

OLLAMA GGUF

llama · 256.74M · F16

Not Rec.

Jul 5, 2026 · Apple M4 Pro

Global Score
62 vs 34
Hardware Fit
35 vs 100
Quality Score
73 vs 6

Hardware

qwen3.5-4b-mlx microllm-250m:latest
MachineMac miniMac mini
CPUApple M4 ProApple M4 Pro
Cores1412
RAM64 GB24 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 15.7.4macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-4b-mlx microllm-250m:latest
Tokens/sec0.0291.6
First chunk5548 ms50 ms
TTFT5.5 s79 ms
Load timeN/A0.0 s
Memory usage2.9 GB0.6 GB
Memory %5%2%

HW Fit Score Breakdown

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

microllm-250m:latest

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

Quality

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate 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 qwen3.5-4b-mlx 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