Oh and I typically get 16-20 tok/s running a 32b model on Ollama using Open WebUI. Also I have experienced issues with 4-bit quantization for the K/V cache on some models myself so just FYI
- 0 Posts
- 4 Comments
Joined 5 years ago
Cake day: June 30th, 2020
You are not logged in. If you use a Fediverse account that is able to follow users, you can follow this user.
It really depends on how you quantize the model and the K/V cache as well. This is a useful calculator. https://smcleod.net/vram-estimator/ I can comfortably fit most 32b models quantized to 4-bit (usually KVM or IQ4XS) on my 3090’s 24 GB of VRAM with a reasonable context size. If you’re going to be needing a much larger context window to input large documents etc then you’d need to go smaller with the model size (14b, 27b etc) or get a multi GPU set up or something with unified memory and a lot of ram (like the Mac Minis others are mentioning).
1·1 month agoIs it possible to use StreetComplete on iOS?
Looks like it now has Docling Content Extraction Support for RAG. Has anyone used Docling much?