Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

tinyllama

OLLAMA GGUF
Marginal

Mar 6, 2026 · Apple M4

Global Score
62 vs 43
Hardware Fit
35 vs 100
Quality Score
73 vs 19

Hardware

qwen3.5-4b-mlx tinyllama
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-4b-mlx tinyllama
Tokens/sec0.0133.4
First chunk5548 ms61 ms
TTFT5.5 s61 ms
Load timeN/A0.5 s
Memory usage2.9 GB0.2 GB
Memory %5%1%

HW Fit Score Breakdown

qwen3.5-4b-mlx

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

tinyllama

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

tinyllama

Reasoning
2/20
Coding
2/20
Instruction
7/20
Structured
5/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
View qwen3.5-4b-mlx details | View tinyllama 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