Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

Global Score
53 vs 79
Hardware Fit
82 vs 57
Quality Score
41 vs 89

Hardware

qwen3.5:4b-mlx qwen3.5:27b
MachineMac miniAZW GTR Pro
CPUApple M2AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores832
RAM8 GB125 GB
GPUApple M2Integrated / Apple Silicon
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5:4b-mlx qwen3.5:27b
Tokens/sec24.710.7
First chunk302 ms341 ms
TTFT7.4 s341 ms
Load time3.2 s10.2 s
Memory usage3.8 GB39.7 GB
Memory %47%32%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

qwen3.5:27b

Speed
9/50
TTFT
20/20
Memory
28/30

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

qwen3.5:27b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b-mlx details | View qwen3.5:27b 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