Downloads · 30 days
39
13% of all-time downloads
salamandra-7b-instruct-2606-GGUF
jordimas/salamandra-7b-instruct-2606-GGUF
salamandra-7b-instruct-2606-GGUF is a machine learning model from jordimas. 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 llama.cpp. The card lists the license as apache-2.0.
GGUF conversions of BSC-LT/salamandra-7b-instruct-2606, produced with llama.cpp commit b81c99b47.
All-time downloads
308
Public
Repo size
28.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf28.7 GB · 100%
At a glance
- Library
- llama.cpp
- License
- apache-2.0
- Access
- Public
- Created
- Sep 19, 2026
- Updated
- Sep 19, 2026
- SHA
- f9c3fe5f
Base models
Model card
From the Hugging Face model README
Salamandra 7B Instruct 2606 — GGUF
GGUF conversions of BSC-LT/salamandra-7b-instruct-2606, produced with llama.cpp commit b81c99b47.
| File | Type | Size |
|---|---|---|
salamandra-7b-instruct-2606.BF16.gguf | BF16, unquantized | 15.5 GB |
salamandra-7b-instruct-2606.Q8_0.gguf | Q8_0 | 7.7 GB |
salamandra-7b-instruct-2606.Q4_K_M.gguf | Q4_K_M | 4.6 GB |
convert_hf_to_gguf.py is the conversion script used for the BF16 export. The Q8_0 and Q4_K_M files were produced from that BF16 GGUF with llama-quantize.
Use with llama.cpp
llama-cli -hf-repo jordimas/salamandra-7b-instruct-2606-GGUF \
-hf-file salamandra-7b-instruct-2606.Q4_K_M.gguf \
-cnv
The upstream model is released under Apache-2.0. Refer to the upstream model card for intended use, limitations, and training details.
- Library
- llama.cpp
- License
- apache-2.0
- Created
- Sep 19, 2026
- Updated
- Sep 19, 2026