Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
tgtweak
66 days ago
|
parent
|
context
|
favorite
| on:
Qwen3.6-27B: Flagship-Level Coding in a 27B Dense ...
Depends entirely on quantization. Q6_K with max context length (262144) is ~40GB of VRAM.
Q8 with the same context wouldn't fit in 48GB of VRAM, it did with 128k of context.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Q8 with the same context wouldn't fit in 48GB of VRAM, it did with 128k of context.