GGUF models by Savyasaachin

39 GGUF models quantized by Savyasaachin on Hugging Face. Sizes run from 6M to 23.6B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
DE
Qwen2.5 Coder 7B
DeepSeek · Savyasaachin
Params7.62B
Context32K
Smallest5.4 GB
CodingTool use
DE
Deepseek Coder 6.7b Instruct
DeepSeek · Savyasaachin
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
Qwen3 Shining Lucy CODER 3.4B Brainstorm20x E32
Qwen · Savyasaachin
Params3.38B
Context40K
Smallest3.6 GB
CodingReasoning
SN
Snowflake Arctic Embed L v2.0
Snowflake · Savyasaachin
Params567M
Context8K
Smallest0.6 GB
Embedding
JI
Jina Embeddings v3
Jina · Savyasaachin
Params558M
Context8K
Smallest0.6 GB
Embedding
SA
Sarvam Translate
Sarvam · Savyasaachin
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
GE
Gemma 3 4b It Claude
Gemma · Savyasaachin
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
MD
Mdbr Leaf Ir
Mdbr · Savyasaachin
Params23M
Context512
Smallest0.0 GB
Embedding
SA
Sarvam 1
Sarvam · Savyasaachin
Params2.53B
Context8K
Smallest2.7 GB
Tool use
SA
Sarvam Translate
Sarvam · Savyasaachin
Params3.88B
Context128K
Smallest4.1 GB
GGUF
SA
Sarvam 1 2b Instruct
Sarvam · Savyasaachin
Params2.53B
Context8K
Smallest2.7 GB
GGUF
GE
bge reranker v2 gemma Q8 0
Gemma · Savyasaachin
Params2.51B
Context8K
Smallest2.7 GB
Embedding
SA
sarvam ai finetuning distillation v4 1 F32
Sarvam · Savyasaachin
Params24M
Context—
Smallest0.1 GB
GGUF
GE
Gemma3B OCR
Gemma · Savyasaachin
Params6M
Context128K
Smallest0.0 GB
GGUF
DE
Deepseek Coder 6.7b Instruct
DeepSeek · Savyasaachin
Params6.74B
Context16K
Smallest4.8 GB
Coding
QW
Qwen2.5 3B Law Instruct
Qwen · Savyasaachin
Params6M
Context32K
Smallest0.0 GB
Tool use
GE
Shadows Gemma 3 1B
Gemma · Savyasaachin
Params1B
Context32K
Smallest1.1 GB
Reasoning
SA
Sarvam Translate
Sarvam · Savyasaachin
Params3.88B
Context128K
Smallest2.8 GB
GGUF
SA
Sarvam M
Sarvam · Savyasaachin
Params23.6B
Context32K
Smallest13.4 GB
Reasoning
KR
Krutrim 2 Instruct
Krutrim · Savyasaachin
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · Savyasaachin
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
SM
SmolDocling 256M Preview
Smoldocling · Savyasaachin
Params163M
Context8K
Smallest0.2 GB
Vision
IN
Indian Legal Assitant Q6 K
Indian · Savyasaachin
Params8.03B
Context128K
Smallest6.6 GB
GGUF
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · Savyasaachin
Params8.03B
Context128K
Smallest8.5 GB
ReasoningTool use
SA
Sarvam Translate
Sarvam · Savyasaachin
Params3.88B
Context128K
Smallest3.2 GB
GGUF
DE
Deepseek Coder 7b Instruct v1.5
DeepSeek · Savyasaachin
Params6.91B
Context4K
Smallest5.7 GB
Coding
LE
Legal SLM
Legal · Savyasaachin
Params35M
Context—
Smallest0.1 GB
GGUF
QW
Qwen2.5 3B Law Instruct
Qwen · Savyasaachin
Params3B
Context—
Smallest0.0 GB
GGUF
LL
Viber Indian Law Unsloth Llama 3.1 8B Q4 K M
Llama · Savyasaachin
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
GE
Gemma 2 9b It
Gemma · Savyasaachin
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF

About Savyasaachin on Hugging Face

Savyasaachin has published 39 GGUF models that ggufmodels.com tracks, across families such as Sarvam, Gemma and DeepSeek. The most downloaded are Qwen2.5 Coder 7B, Deepseek Coder 6.7b Instruct and Qwen3 Shining Lucy CODER 3.4B Brainstorm20x E32.

The quants Savyasaachin publishes most often are Q8_0 (14), Q4_K_M (7), F32 (6) and Q6_K (3). Their Q4_K_M files range from 2.5 to 7.5 GB. Parameter counts run from 6M to 23.6B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has Savyasaachin published?

39 models are listed here, mainly from the Sarvam, Gemma and DeepSeek families. The most downloaded is Qwen2.5 Coder 7B.

Which quants does Savyasaachin publish?

The most common are Q8_0 (14 models), Q4_K_M (7 models), F32 (6 models) and Q6_K (3 models).

Keep browsing