qwen3.5:latest

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Not Rec.

Mar 8, 2026 · Apple M4

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score

34 vs 74

Hardware Fit

58 vs 99

Quality Score

23 vs 63

Hardware

qwen3.5:latest llama3.2:3b

MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUApple M4Cortex-A78AE

Cores106

RAM16 GB7 GB

GPUApple M4Integrated / Unknown

OSmacOS 26.3Ubuntu 22.04.5 LTS

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.5:latest llama3.2:3b

Tokens/sec13.321.1

First chunk438 ms1032 ms

TTFT19.8 s1.0 s

Load time0.2 s8.4 s

Memory usage8.0 GB2.4 GB

Memory %50%32%

HW Fit Score Breakdown

qwen3.5:latest

Speed

32/50

TTFT

1/20

Memory

25/30

llama3.2:3b

Speed

50/50

TTFT

20/20

Memory

29/30

Quality

qwen3.5:latest

Reasoning

6/20

Coding

1/20

Instruction

3/20

Structured

0/15

Math

5/15

Multilingual

8/10

Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

llama3.2:3b

Reasoning

10/20

Coding

14/20

Instruction

15/20

Structured

12/15

Math

3/15

Multilingual

9/10

Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

View qwen3.5:latest details | View llama3.2:3b 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