Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
int_19h
5 months ago
|
parent
|
context
|
favorite
| on:
Cerebras launches Qwen3-235B, achieving 1.5k token...
GGML hasn't been a thing for some time, and GGUF (its successor) has features such as "importance matrix" quantization that is all about quantizing adaptively. Then there's all the stuff that Unsloth does, e.g.:
https://unsloth.ai/blog/dynamic-v2
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: