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.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
SA
Salamandra 7b Instruct
Salamandra · RichardErkhov
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Salamandra 7b Instruct Uncensored Abliterated
Salamandra · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Salamandra 2b Instruct
Salamandra · mradermacher
Params2.25B
Context8K
Q4_K_M1.5 GB
Coding
SA
Salamandra 7b Instruct 2606
Salamandra · mradermacher
Params7.77B
Context160K
Q4_K_M4.9 GB
Reasoning
SA
Salamandra 7b Instruct Uncensored Abliterated
Salamandra · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Salamandra 2b
Salamandra · RichardErkhov
Params2.25B
Context8K
Q4_K_M1.5 GB
GGUF
SA
Salamandra 7b Instruct Tools 20260108
Salamandra · mradermacher
Params7.77B
Context16K
Q4_K_M4.9 GB
Tool use
SA
Salamandra 7b Instruct 2606
Salamandra · mradermacher
Params7.77B
Context160K
Q4_K_M4.9 GB
Reasoning
SA
Salamandra 2b Instruct
Salamandra · RichardErkhov
Params2.25B
Context8K
Q4_K_M1.5 GB
GGUF
SA
salamandra 2b
Salamandra · robbiemu
Params2.25B
Context8K
Q4_K_M2.1 GB
Coding
SA
Salamandra 7b
Salamandra · RichardErkhov
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
SA
salamandra 2b instruct
Salamandra · robbiemu
Params2.25B
Context8K
Q4_K_M2.1 GB
Coding
SA
Salamandra 7b RAG v2
Salamandra · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
Coding
SA
salamandra 7b instruct
Salamandra · cstr
Params7.77B
Context8K
Q4_K_M4.9 GB
Coding
SA
salamandra 7b aligned EADOP
Salamandra · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Salamandra 2b Instruct
Salamandra · mradermacher
Params2.25B
Context8K
Q4_K_M1.5 GB
Coding
SA
Salamandra 7b Instruct
Salamandra · hdnh2006
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Salamandra 7b Instruct
Salamandra · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Salamandra TAV 7b
Salamandra · mradermacher
Params7.78B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Salamandra 7b RAG v2
Salamandra · RichardErkhov
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Salamandra 7b Instruct 2606
Salamandra · Fr4nkSt3in
Params7.77B
Context160K
Smallest15.5 GB
GGUF
SA
Salamandra TAV 7b
Salamandra · mradermacher
Params7.78B
Context8K
Q4_K_M4.9 GB
GGUF
SA
cecilia 2b v0.1
Salamandra · JorG941
Params2.25B
Context8K
Q4_K_M1.5 GB
GGUF
SA
salamandra 2B instruct ultrachat
Salamandra · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Salamandra 7b Instruct Aina Hack
Salamandra · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
Coding
SA
Salamandra 2b Instruct
Salamandra · hdnh2006
Params2.25B
Context8K
Q4_K_M1.5 GB
GGUF
SA
Aitana 2B S base
Salamandra · gplsi
Params2.25B
Context8K
Smallest4.5 GB
GGUF
SA
salamandra-2b-smol-smoltalk-sv
Salamandra · mradermacher
Params2.25B
Context8K
Q4_K_M1.5 GB
GGUF
SA
Salamandra 7b Instruct
Salamandra · tensorblock
Params7.77B
Context8K
Smallest3.3 GB
Coding
SA
Salamandra 2b Function Calling Tulu If Bilingual
Salamandra · mradermacher
Params2.25B
Context8K
Q4_K_M1.5 GB
Tool use

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.

Keep browsing