Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
53 vs 76
Hardware Fit
81 vs 100
Quality Score
41 vs 66

Hardware

qwen3.5:4b-mlx hf.co/empero-ai/Qw…
MachineMac miniMacBook Pro
CPUApple M2Apple M1 Pro
Cores810
RAM8 GB16 GB
GPUApple M2Apple M1 Pro
OSmacOS 26.5.2macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx hf.co/empero-ai/Qw…
Tokens/sec24.840.3
First chunk317 ms101 ms
TTFT7.4 s101 ms
Load time0.0 s2.7 s
Memory usage3.9 GB4.5 GB
Memory %49%28%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
25/30

hf.co/empero-ai/Qwen3.8…

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

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

hf.co/empero-ai/Qwen3.8…

Reasoning
11/20
Coding
10/20
Instruction
12/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b-mlx details | View hf.co/empero-ai/Qw… 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