Salamandra GGUF models
81 GGUF models in the Salamandra family, quantized by 29 uploaders. Sizes run from 2.25B to 7.78B parameters. The longest trained context is 160K tokens.
About the Salamandra GGUF models
Salamandra is represented on ggufmodels.com by 81 GGUF models, quantized by 29 uploaders on Hugging Face. The most downloaded are Salamandra 7b Instruct, Salamandra 7b Instruct Uncensored Abliterated and Salamandra 2b Instruct. Parameter counts run from 2.25B to 7.78B, and the longest trained context window is 160K tokens.
A Q4_K_M file of a Salamandra model is between 1.5 to 4.9 GB, which is the quant most people start with. Most files come from mradermacher (30), franciscobdl (7) and RichardErkhov (5). The quants you will meet most often are Q4_K_M (55), Q5_K_M (50), Q8_0 (48) and Q6_K (43), where the number is how many models offer that quant.
Frequently asked questions
Which Salamandra GGUF should I download?
The most downloaded Salamandra GGUF here is Salamandra 7b Instruct. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Salamandra model need?
Q4_K_M files of Salamandra models on this site range from 1.5 to 4.9 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Salamandra GGUF files come from?
The most common quantizers here are mradermacher, franciscobdl and RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.