Sarvam GGUF models

111 GGUF models in the Sarvam family, quantized by 56 uploaders. Sizes run from 13M to 106B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
SA
sarvam 30b GGUF IQ2 M IQ1 M
Sarvam · Aaravomega
Params32.2B
Context128K
Smallest7.9 GB
ReasoningTool use
SA
sarvam 105b GGUF IQ2 M IQ1 M
Sarvam · Aaravomega
Params106B
Context128K
Smallest0.3 GB
GGUF
SA
Sarvamai.Sarvam 30b
Sarvam · DevQuasar
Params32.2B
Context128K
Smallest12.2 GB
GGUF
SA
Sarvam 1
Sarvam · bartowski
Params2.53B
Context8K
Q4_K_M1.5 GB
Tool use
SA
Sarvam 30b
Sarvam · sarvamai
Params32.2B
Context128K
Q4_K_M19.6 GB
GGUF
SA
Sarvam M
Sarvam · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
SA
Sarvam Translate
Sarvam · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
SA
Sarvam 30b Uncensored
Sarvam · mradermacher
Params32.2B
Context128K
Q4_K_M19.6 GB
ReasoningTool use
SA
Sarvam 2b v0.5
Sarvam · mradermacher
Params2.51B
Context8K
Q4_K_M1.5 GB
GGUF
SA
Sarvam Translate
Sarvam · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
SA
Sarvam 1
Sarvam · mradermacher
Params2.53B
Context8K
Q4_K_M1.5 GB
Tool use
SA
Sarvam 1 Hindi Marathi
Sarvam · mradermacher
Params2.53B
Context8K
Q4_K_M1.5 GB
Tool use
SA
Sarvam 30b Uncensored
Sarvam · mradermacher
Params32.2B
Context128K
Q4_K_M19.6 GB
ReasoningTool use
SA
Sarvam 1
Sarvam · QuantFactory
Params2.53B
Context8K
Q4_K_M1.5 GB
Tool use
SA
sarvam translate 1bit
Sarvam · Mugunth123
Params3.88B
Context128K
Smallest1.1 GB
GGUF
SA
Sarvam M
Sarvam · lmstudio-community
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
SA
Sarvam 30b Full
Sarvam · Sumitc13
Params32.2B
Context128K
Q4_K_M19.6 GB
ReasoningTool use
SA
Sarvam 30B ROCmFP4
Sarvam · kingjones777
Params32.2B
Context128K
Smallest17.4 GB
ReasoningTool use
SA
Sarvam 105b
Sarvam · sarvamai
Params106B
Context128K
Q4_K_M64.2 GB
ReasoningTool use
SA
Sarvam 2b v0.5
Sarvam · QuantFactory
Params2.51B
Context8K
Q4_K_M1.5 GB
GGUF
SA
Sarvamai.Sarvam M
Sarvam · DevQuasar
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
SA
sarvam translate 1.58bit
Sarvam · Mugunth123
Params3.88B
Context128K
Smallest1.2 GB
GGUF
SA
sarvam translate 2bit
Sarvam · Mugunth123
Params3.88B
Context128K
Smallest1.5 GB
GGUF
SA
Sarvam 1
Sarvam · mradermacher
Params2.53B
Context8K
Q4_K_M1.5 GB
Tool use
SA
Sarvam 30b Full
Sarvam · shiva1294
Params32.2B
Context128K
Q4_K_M19.6 GB
ReasoningTool use
SA
sarvam 30b topo governed
Sarvam · frankmorales2020
Params32.2B
Context128K
Smallest34.2 GB
ReasoningTool use
SA
Sarvam 1
Sarvam · MaziyarPanahi
Params2.53B
Context8K
Smallest1.8 GB
Tool use
SA
sarvam m
Sarvam · ReallyFloppyPenguin
Params23.6B
Context32K
Smallest13.4 GB
Reasoning
SA
Sarvam 1
Sarvam · DevQuasar-3
Params2.53B
Context8K
Q4_K_M1.5 GB
Tool use
SA
Aoxo Sarvam 30b Uncensored
Sarvam · ThatCultivator
Params32.2B
Context128K
Q4_K_M19.6 GB
ReasoningTool use

About the Sarvam GGUF models

Sarvam is represented on ggufmodels.com by 111 GGUF models, quantized by 56 uploaders on Hugging Face. The most downloaded are sarvam 30b GGUF IQ2 M IQ1 M, sarvam 105b GGUF IQ2 M IQ1 M and Sarvamai.Sarvam 30b. Parameter counts run from 13M to 106B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Sarvam model is between 1.5 to 64.2 GB, which is the quant most people start with. Most files come from tifin-india (12), Savyasaachin (11) and mradermacher (8). The quants you will meet most often are Q4_K_M (46), Q8_0 (39), Q6_K (26) and Q5_K_M (22), where the number is how many models offer that quant.

Frequently asked questions

Which Sarvam GGUF should I download?

The most downloaded Sarvam GGUF here is sarvam 30b GGUF IQ2 M IQ1 M. 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 Sarvam model need?

Q4_K_M files of Sarvam models on this site range from 1.5 to 64.2 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 Sarvam GGUF files come from?

The most common quantizers here are tifin-india, Savyasaachin and mradermacher. 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