Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

hf.co/bloomer010/Ling-3.0-tiny-GGUF:Q8_0

OLLAMA GGUF

bailingmoe3 · 7.89B · unknown

Good

Aug 23, 2026 · Apple M1 Pro

Global Score
62 vs 68
Hardware Fit
35 vs 93
Quality Score
73 vs 57

Hardware

qwen3.5-4b-mlx hf.co/bloomer010/L…
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1410
RAM64 GB16 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 15.7.4macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-4b-mlx hf.co/bloomer010/L…
Tokens/sec0.058.9
First chunk5548 ms208 ms
TTFT5.5 s208 ms
Load timeN/A4.4 s
Memory usage2.9 GB8.5 GB
Memory %5%53%

HW Fit Score Breakdown

qwen3.5-4b-mlx

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

hf.co/bloomer010/Ling-3…

Speed
50/50
TTFT
20/20
Memory
23/30

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

hf.co/bloomer010/Ling-3…

Reasoning
19/20
Coding
17/20
Instruction
3/20
Structured
1/15
Math
15/15
Multilingual
2/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

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