robbiemu/Salesforce_Llama-xLAM-2:8b-fc-r-q3_K

personal testimonial (project results)

Q3_K_M: many errors for a large graph of calls, very fast
Q5_K_M: still meaningful errors
Q8_0: still some meaningful errors, still kinda fast
bf16: no apparent improvement, no longer very fast.

quantized models direct from hf.co tensorblock/Salesforce_Llama-xLAM-2-8b-fc-r-GGUF

BF16 I had to make myself. (with llama.cpp b6236)

Salesforce/Llama-xLAM-2-8b-fc-r - GGUF

This repo contains GGUF format model files for Salesforce/Llama-xLAM-2-8b-fc-r.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5165.

Our projects

Forge

An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

Prompt template

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}
<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Model file specification

Filename	Quant type	File Size	Description
Llama-xLAM-2-8b-fc-r-Q2_K.gguf	Q2_K	3.179 GB	smallest, significant quality loss - not recommended for most purposes
Llama-xLAM-2-8b-fc-r-Q3_K_S.gguf	Q3_K_S	3.665 GB	very small, high quality loss
Llama-xLAM-2-8b-fc-r-Q3_K_M.gguf	Q3_K_M	4.019 GB	very small, high quality loss
Llama-xLAM-2-8b-fc-r-Q3_K_L.gguf	Q3_K_L	4.322 GB	small, substantial quality loss
Llama-xLAM-2-8b-fc-r-Q4_0.gguf	Q4_0	4.661 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Llama-xLAM-2-8b-fc-r-Q4_K_S.gguf	Q4_K_S	4.693 GB	small, greater quality loss
Llama-xLAM-2-8b-fc-r-Q4_K_M.gguf	Q4_K_M	4.921 GB	medium, balanced quality - recommended
Llama-xLAM-2-8b-fc-r-Q5_0.gguf	Q5_0	5.599 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Llama-xLAM-2-8b-fc-r-Q5_K_S.gguf	Q5_K_S	5.599 GB	large, low quality loss - recommended
Llama-xLAM-2-8b-fc-r-Q5_K_M.gguf	Q5_K_M	5.733 GB	large, very low quality loss - recommended
Llama-xLAM-2-8b-fc-r-Q6_K.gguf	Q6_K	6.596 GB	very large, extremely low quality loss
Llama-xLAM-2-8b-fc-r-Q8_0.gguf	Q8_0	8.541 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Salesforce_Llama-xLAM-2-8b-fc-r-GGUF --include "Llama-xLAM-2-8b-fc-r-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Salesforce_Llama-xLAM-2-8b-fc-r-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'