Sambalingo GGUF models

82 GGUF models in the Sambalingo family, quantized by 15 uploaders. Sizes run from 2.49B to 69.4B parameters. The longest trained context is 4K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
SA
SambaLingo Hungarian Chat
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Japanese Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Arabic Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Arabic Chat 70B
Sambalingo · mradermacher
Params69.4B
Context4K
Q4_K_M41.7 GB
GGUF
SA
SambaLingo Arabic Base
Sambalingo · RichardErkhov
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Thai Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Hungarian Chat 70B
Sambalingo · mradermacher
Params69.4B
Context4K
Q4_K_M41.7 GB
GGUF
SA
SambaLingo Hungarian Chat
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Slovenian Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Serbian Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Thai Chat 70B
Sambalingo · mradermacher
Params69.4B
Context4K
Q4_K_M41.7 GB
GGUF
SA
SambaLingo Arabic Chat 70B
Sambalingo · RichardErkhov
Params69.4B
Context4K
Q4_K_M41.7 GB
GGUF
SA
SambaLingo Bulgarian Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Hungarian Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Arabic Base 70B
Sambalingo · RichardErkhov
Params69.4B
Context4K
Q4_K_M41.7 GB
GGUF
SA
SambaLingo Japanese Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Turkish Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Hungarian Base 70B
Sambalingo · mradermacher
Params69.4B
Context4K
Q4_K_M41.7 GB
GGUF
SA
SambaLingo Russian Chat
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Russian Chat
Sambalingo · RichardErkhov
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Arabic Chat
Sambalingo · RichardErkhov
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Thai Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Turkish Chat
Sambalingo · RichardErkhov
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Slovenian Chat
Sambalingo · RichardErkhov
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Serbian Chat
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Hungarian Chat
Sambalingo · RichardErkhov
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Russian Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Arabic Base 70B
Sambalingo · mradermacher
Params69.4B
Context4K
Q4_K_M41.7 GB
GGUF
SA
sambanovasystems.SambaLingo Hungarian Base
Sambalingo · DevQuasar
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SambaLingo Slovenian Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF

About the Sambalingo GGUF models

Sambalingo is represented on ggufmodels.com by 82 GGUF models, quantized by 15 uploaders on Hugging Face. The most downloaded are SambaLingo Hungarian Chat, SambaLingo Japanese Base and SambaLingo Arabic Base. Parameter counts run from 2.49B to 69.4B, and the longest trained context window is 4K tokens.

A Q4_K_M file of a Sambalingo model is between 4.2 to 41.7 GB, which is the quant most people start with. Most files come from mradermacher (48), RichardErkhov (8) and NikolayKozloff (7). The quants you will meet most often are Q4_K_M (66), Q5_K_M (62), Q2_K (62) and Q5_K_S (59), where the number is how many models offer that quant.

Frequently asked questions

Which Sambalingo GGUF should I download?

The most downloaded Sambalingo GGUF here is SambaLingo Hungarian Chat. 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 Sambalingo model need?

Q4_K_M files of Sambalingo models on this site range from 4.2 to 41.7 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 Sambalingo GGUF files come from?

The most common quantizers here are mradermacher, RichardErkhov and NikolayKozloff. 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