[wild_egg]

Don't have a GPU so tried the CPU option and got 0.6t/s on my old 2018 laptop using their llama.cpp fork.

Then found out they didn't implement AVX2 for their Q1_0_g128 CPU kernel. Added that and getting ~12t/s which isn't shabby for this old machine.

Cool model.

[UncleOxidant]

Are you getting anything besides gibberish out of it? I tried their recommended commandline and it's dog slow even though I built their llama.cpp fork with AVX2 enabled. This is what I get:

    $ ./build/bin/llama-cli     -hf prism-ml/Bonsai-8B-gguf -p "Explain quantum computing in simple terms." -n 256 --temp 0.5 --top-p 0.85 --top-k 20 -ngl 99
    > Explain quantum computing in simple terms.

     \( ,

      None ( no for the. (,./. all.2... the                                                                                                                                ..... by/

EDIT: It runs fine in their collab notebook. Looking at that you have to do: git checkout prism (in the llama.cpp repo) before you build. That's a missing instruction if you're going straight to their fork of llama.cpp. Works fine now.

[UncleOxidant]

UPDATE: I was using the llama.cpp CPU backend and was still getting gibberish. On Google colab they're running with CUDA. I turned Claude loose on the problem and it discovered a problem in the llama.cpp CPU backend code where a float was being converted to an int and basically going to 0. Now it runs fine locally with the CPU backend.

[gorgonical]

Mind sharing the fix as a patch? I would like to run it this way, too.

[UncleOxidant]

https://github.com/philtomson/llama.cpp

[gorgonical]

Works like a charm for me, just like for you. Getting ~8 tok/s on my middle-of-the-road workstation laptop. Thanks for this!

[cubefox]

"Not shabby" is a big understatement.

[ddtaylor]

Why so?

[boxedemp]

Because it's the opposite of shabby

[ddtaylor]

What are the reasons?