Sarashina GGUF models

99 GGUF models in the Sarashina family, quantized by 34 uploaders. Sizes run from 793M to 70.1B parameters. The longest trained context is 16K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
SA
Sarashina2.2 3b Instruct v0.1
Sarashina · mmnga
Params3.36B
Context8K
Q4_K_M2.1 GB
GGUF
SA
Sarashina2.2 1b Instruct v0.1
Sarashina · mmnga
Params1.41B
Context8K
Q4_K_M0.9 GB
GGUF
SA
Sarashina2.2 0.5b Instruct v0.1
Sarashina · mmnga
Params793M
Context8K
Q4_K_M0.5 GB
GGUF
SA
Sarashina2.2 0.5b
Sarashina · mradermacher
Params793M
Context8K
Q4_K_M0.5 GB
GGUF
SA
Sarashina2.2 1b
Sarashina · mradermacher
Params1.41B
Context8K
Q4_K_M0.9 GB
GGUF
SA
Sarashina2.2 3b Instruct v0.1
Sarashina · mradermacher
Params3.36B
Context8K
Q4_K_M2.1 GB
Tool use
SA
sarashina2.2 vision 3b
Sarashina · samuraieng
Params3.36B
Context8K
Q4_K_M2.1 GB
Vision
SA
sarashina2 7b
Sarashina · QuantFactory
Params7.32B
Context4K
Q4_K_M4.5 GB
GGUF
SA
Sarashina 13B Finetuned v1
Sarashina · mradermacher
Params13.7B
Context4K
Q4_K_M8.4 GB
GGUF
SA
Sarashina2 7b Abliterated
Sarashina · mradermacher
Params7.32B
Context4K
Q4_K_M4.5 GB
GGUF
SA
Sarashina 13B Finetuned v2
Sarashina · mradermacher
Params13.7B
Context4K
Q4_K_M8.4 GB
GGUF
SA
Sarashina2.1 1b
Sarashina · mmnga
Params1.41B
Context8K
Q4_K_M0.9 GB
GGUF
SA
Sarashina2.2 3b Instruct v0.1
Sarashina · mradermacher
Params3.36B
Context8K
Q4_K_M2.1 GB
Tool use
SA
sarashina2.2-3b-instruct-v0.1
Sarashina · neody
Params3.36B
Context8K
Q4_K_M2.1 GB
Tool use
SA
Sarashina2.2 Vision 3b
Sarashina · mradermacher
Params3.36B
Context8K
Q4_K_M2.1 GB
Vision
SA
Sarashina2 7b It Src
Sarashina · RyoSpiralArchitect
Params7.32B
Context4K
Q4_K_M4.5 GB
GGUF
SA
Sarashina2.2 3b RP v0.1
Sarashina · Aratako
Params3.36B
Context8K
Q4_K_M2.1 GB
RoleplayTool use
SA
Sarashina2.1 1b
Sarashina · mradermacher
Params1.41B
Context8K
Q4_K_M0.9 GB
GGUF
SA
Sarashina 13B Finetuned v3
Sarashina · mradermacher
Params13.7B
Context4K
Q4_K_M8.4 GB
GGUF
SA
Sarashina2.2 3b RP v0.1
Sarashina · mradermacher
Params3.36B
Context8K
Q4_K_M2.1 GB
RoleplayTool use
SA
Sarashina2.2 0.5b Instruct v0.1
Sarashina · mradermacher
Params793M
Context8K
Q4_K_M0.5 GB
Tool use
SA
Sarashina 13B Finetuned v2
Sarashina · mradermacher
Params13.7B
Context4K
Q4_K_M8.4 GB
GGUF
SA
HACHI Summary Ja sarashina2.2 0.5b instruct v0.1
Sarashina · hachi-intelligence
Params793M
Context8K
Smallest0.5 GB
Tool use
SA
Sarashina2.2 3B OpenScience NoReasoning 300k
Sarashina · mradermacher
Params3.36B
Context8K
Q4_K_M2.1 GB
ReasoningTool use
SA
Sarashina2.2 Vision 3b
Sarashina · mradermacher
Params3.36B
Context8K
Q4_K_M2.1 GB
Vision
SA
Sarashina2.1 1b
Sarashina · QuantFactory
Params1.41B
Context8K
Q4_K_M0.9 GB
GGUF
SA
Sarashina2 70b
Sarashina · mradermacher
Params70.1B
Context8K
Q4_K_M42.2 GB
GGUF
SA
Sbintuitions.Sarashina2.2 0.5b Instruct v0.1
Sarashina · DevQuasar-8
Params793M
Context8K
Q4_K_M0.5 GB
Tool use
SA
Sarashina2 7b Abliterated
Sarashina · mradermacher
Params7.32B
Context4K
Q4_K_M4.5 GB
GGUF
SA
Sarashina2 13b
Sarashina · RichardErkhov
Params13.7B
Context4K
Q4_K_M8.4 GB
GGUF

About the Sarashina GGUF models

Sarashina is represented on ggufmodels.com by 99 GGUF models, quantized by 34 uploaders on Hugging Face. The most downloaded are Sarashina2.2 3b Instruct v0.1, Sarashina2.2 1b Instruct v0.1 and Sarashina2.2 0.5b Instruct v0.1. Parameter counts run from 793M to 70.1B, and the longest trained context window is 16K tokens.

A Q4_K_M file of a Sarashina model is between 0.5 to 42.2 GB, which is the quant most people start with. Most files come from mradermacher (34), FiShota (8) and keisuke-miyako (7). The quants you will meet most often are Q4_K_M (89), Q5_K_M (69), Q6_K (64) and Q8_0 (59), where the number is how many models offer that quant.

Frequently asked questions

Which Sarashina GGUF should I download?

The most downloaded Sarashina GGUF here is Sarashina2.2 3b Instruct v0.1. 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 Sarashina model need?

Q4_K_M files of Sarashina models on this site range from 0.5 to 42.2 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 Sarashina GGUF files come from?

The most common quantizers here are mradermacher, FiShota and keisuke-miyako. 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