Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

qwen3:1.7b

OLLAMA GGUF

qwen3 · 2.0B · Q4_K_M

Good

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
53 vs 72
Hardware Fit
82 vs 92
Quality Score
41 vs 63

Hardware

qwen3.5:4b-mlx qwen3:1.7b
MachineMac miniAZW GTR Pro
CPUApple M2AMD RYZEN AI MAX+ 395
Cores832
RAM8 GB125 GB
GPUApple M2AMD Radeon 8060S
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3.5:4b-mlx qwen3:1.7b
Tokens/sec24.7120.7
First chunk302 ms93 ms
TTFT7.4 s1.5 s
Load time3.2 s2.5 s
Memory usage3.8 GB5.8 GB
Memory %47%5%

HW Fit Score Breakdown

qwen3.5:4b-mlx

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

qwen3:1.7b

Speed
50/50
TTFT
12/20
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

qwen3:1.7b

Reasoning
13/20
Coding
6/20
Instruction
13/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:4b-mlx details | View qwen3:1.7b 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