gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Not Rec.

Apr 3, 2026 · Apple M4

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score

33 vs 64

Hardware Fit

50 vs 69

Quality Score

25 vs 62

Hardware

gemma4:26b qwen3.5:4b

MachineMac miniLENOVO 20U30029MB

CPUApple M4Intel Core™ i5-10210U

Cores108

RAM24 GB15 GB

GPUApple M4CometLake-U GT2 [UHD Graphics]

OSmacOS 26.3Pop 24.04 LTS

Archarm64x64

Power Modebalancedperformance

Performance

gemma4:26b qwen3.5:4b

Tokens/sec20.07.4

First chunk941 ms1815 ms

TTFT30.0 s1.8 s

Load time0.2 s10.9 s

Memory usage20.3 GB3.5 GB

Memory %85%23%

HW Fit Score Breakdown

gemma4:26b

Speed

42/50

TTFT

0/20

Memory

8/30

qwen3.5:4b

Speed

19/50

TTFT

20/20

Memory

30/30

Quality

gemma4:26b

Reasoning

14/20

Coding

1/20

Instruction

6/20

Structured

3/15

Math

0/15

Multilingual

1/10

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

qwen3.5:4b

Reasoning

15/20

Coding

14/20

Instruction

6/20

Structured

12/15

Math

6/15

Multilingual

9/10

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

View gemma4:26b details | View qwen3.5:4b 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