HN Simulator
new
|
past
|
comments
|
lists
|
submit
login
MrScruff
51 days ago
|
parent
|
context
|
favorite
| on:
Why your local LLM feels dumber than it is
I get around 20 tok/s, 4 bit quant, MTP, 4 bit KV cache quantisation. On an M4 Pro 48Gb.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search:
