Downloads · 30 days
16
53% of all-time downloads
nb-llama-3.1-8B-Instruct-exl2
oxfrug/nb-llama-3.1-8B-Instruct-exl2
nb-llama-3.1-8B-Instruct-exl2 is a machine learning model from oxfrug. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for exllamav2. The card lists the license as llama3.1.
ExLlamaV2 / EXL2 quants of NbAiLab/nb-llama-3.1-8B-Instruct.
All-time downloads
30
Public
Repo size
29.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json1.8 MB · 100%
At a glance
- Library
- exllamav2
- License
- llama3.1
- Access
- Public
- Created
- Aug 16, 2026
- Updated
- Aug 16, 2026
- SHA
- a28ada16
Base models
Model card
From the Hugging Face model README
NB-Llama-3.1-8B-Instruct — EXL2
ExLlamaV2 / EXL2 quants of NbAiLab/nb-llama-3.1-8B-Instruct.
Official Hub files are BF16 and GGUF. There was no EXL2 pack.
Converted with ExLlamaV2 0.3.2, lm_head at 6-bit, built-in default calibration. One measurement pass, then each bitrate from measurement.json.
Branches
hf download oxfrug/nb-llama-3.1-8B-Instruct-exl2 --revision 5.0bpw --local-dir ./nb-llama-3.1-8B-Instruct-exl2-5.0bpw
Notes
- License: Meta Llama 3.1 Community License. Keep
NOTICE. - Loader: ExLlamaV2. Not GGUF.
- On PyTorch 2.13 without Flash Attention 2.5.7+, set
config.no_sdpa = Truebefore load.
Source
NbAiLab/nb-llama-3.1-8B-Instruct
← meta-llama/Llama-3.1-8B-Instruct
- Library
- exllamav2
- License
- llama3.1
- Languages
- no, nn, sv, da, en
- Created
- Aug 16, 2026
- Updated
- Aug 16, 2026