Invidious
Token Chaser
Subscribe | 7.7K
 RSS

Token Chaser is where AI meets real-world homelab testing.

I test LLMs, GPUs, local AI tools, servers, and self-hosted setups to find out what actually works — not just what looks good on paper. Expect hands-on benchmarks, hardware experiments, model comparisons, inference speed testing, workflow builds, and practical lessons from running AI at home.

Whether you’re building your first homelab, tuning local LLM performance, comparing GPUs, or just chasing faster tokens, this channel is here to make AI infrastructure easier to understand.

LLMs. Homelabs. Benchmarks. Testing what works.

View channel on YouTube
Switch Invidious Instance
Videos
newest
oldest
popular

15:37

Ornith 35B vs Qwen 3.6 35B | Local Head to Head

Token Chaser

Shared 1 month ago

14K views

13:55

Qwythos 9B vs Qwen3.5 9B | 16Gb vRAM Head-to-Head

Token Chaser

Shared 1 month ago

21K views

14:08

Fusion vs Qwen3.6 27B | Head to Head Coding Battle

Token Chaser

Shared 1 month ago

5K views

16:23

Qwopus3.6-27B Coder vs Qwen3.6-27B | 24GB vRAM Head to Head

Token Chaser

Shared 1 month ago

9.8K views

16:48

I Made Fable 5 and Qwen3.6 27B Build the same Web App

Token Chaser

Shared 1 month ago

23K views

16:35

Claude Fable 5 vs GPT 5.5 | Head to Head Coding Battle

Token Chaser

Shared 1 month ago

24K views

16:26

Gemma4 12B vs 12B QAT | 16GB vRAM Head to Head

Token Chaser

Shared 1 month ago

5.5K views

13:06

Gemma4 12B vs 12B QAT | 16GB vRAM Head to Head Battle

Token Chaser

Shared 1 month ago

16K views

15:11

MiMo-v2.5 vs Qwen3.6 27B | Head to Head Coding Battle

Token Chaser

Shared 2 months ago

3.5K views

13:55

MiniMax-M3 vs Qwen3.6 27B | Head to Head Battle

Token Chaser

Shared 2 months ago

6.8K views

12:12

Gemma4 12B IT vs Qwen3.5 9B |16GB vRAM Head to Head

Token Chaser

Shared 2 months ago

16K views

18:39

Qwen3.7 Max vs Qwen3.6 27B | Head to Head Battle

Token Chaser

Shared 2 months ago

8.2K views

14:55

Opus 4.8 vs Qwopus 27B Local | VPS Sabotage Challenge

Token Chaser

Shared 2 months ago

5.4K views

15:25

Step3.7 Flash vs Qwen3.6 27B | Head to Head

Token Chaser

Shared 2 months ago

6K views

22:16

GPT-5.5 vs Qwen3.6 27B MTP | Local vs Cloud AI Head-to-Head

Token Chaser

Shared 2 months ago

8K views

17:50

Qwopus3.6 35B A3B MTP vs 27B MTP | 24GB vRAM Head-to-Head

Token Chaser

Shared 2 months ago

8.2K views

18:22

Claude Opus 4.8 vs Qwen3.6 27B | Local vs Cloud Head-to-Head

Token Chaser

Shared 2 months ago

22K views

18:41

Qwen3.6 27B vs Claude Opus 4.6 | Local Head-to-Head

Token Chaser

Shared 2 months ago

9.1K views

17:26

Qwen3 Coder Next vs Claude Opus 4.6 | Head-to-Head

Token Chaser

Shared 2 months ago

8.2K views

16:15

Qwopus3.6 27B MTP vs Claude Opus 4.6 | Local vs Cloud Head-to-Head

Token Chaser

Shared 2 months ago

35K views

15:54

Qwen3.6 27B vs Nemotron Super 3 120B | Head-to-Head

Token Chaser

Shared 2 months ago

7.6K views

20:37

Qwen3.6 27B vs Heretic NEO Code 27B on RTX 3090s | Head-to-Head

Token Chaser

Shared 2 months ago

5.9K views

14:24

Qwopus3.6 27B vs Qwen3.6 27B | 24GB vRAM Head-to-Head

Token Chaser

Shared 2 months ago

11K views

18:41

Qwen3.6 27B MTP vs Qwen3.6 27B NON-MTP | 24GB vRAM Head-to-Head

Token Chaser

Shared 2 months ago

5.8K views

21:00

Gemma4 31B vs Qwen3.6 27B on RTX 3090s | Local AI Head-to-Head

Token Chaser

Shared 2 months ago

5K views

20:24

Qwen3.6 27B Q8 vs Claude Sonnet 4.6 | Head-to-Head

Token Chaser

Shared 2 months ago

7.7K views

12:13

Qwen3.6 27B vs 35B Unsloth on RTX 3090s | Head-to-Head

Token Chaser

Shared 2 months ago

12K views

13:37

Qwen3.6 27B vs 35B A3B on RTX 3090s | Local AI Head-to-Head

Token Chaser

Shared 2 months ago

7K views