qwen3.5:latest

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Not Rec.

Mar 8, 2026 · Apple M4

gemma4:e4b

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score

34 vs 84

Hardware Fit

58 vs 98

Quality Score

23 vs 78

Hardware

qwen3.5:latest gemma4:e4b

MachineMac miniAZW GTR Pro

CPUApple M4AMD RYZEN AI MAX+ 395

Cores1032

RAM16 GB125 GB

GPUApple M4Radeon 8060S

OSmacOS 26.3Ubuntu 24.04.4 LTS

Archarm64x64

Power Modebalancedperformance

Performance

qwen3.5:latest gemma4:e4b

Tokens/sec13.353.0

First chunk438 ms214 ms

TTFT19.8 s214 ms

Load time0.2 s3.1 s

Memory usage8.0 GB15.0 GB

Memory %50%12%

HW Fit Score Breakdown

qwen3.5:latest

Speed

32/50

TTFT

1/20

Memory

25/30

gemma4:e4b

Speed

48/50

TTFT

20/20

Memory

30/30

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

gemma4:e4b

Reasoning

14/20

Coding

17/20

Instruction

15/20

Structured

15/15

Math

7/15

Multilingual

10/10

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

View qwen3.5:latest details | View gemma4:e4b 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