GGUF models by batiai

39 GGUF models quantized by batiai on Hugging Face. Sizes run from 596M to 1570B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen Qwen3.6 27B
Qwen · batiai
Params27B
Context256K
Q4_K_M16.5 GB
Vision
QW
Qwen3.8 27B
Qwen · batiai
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
QW
Qwen Qwen3.6 35B A3B
Qwen · batiai
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
GL
GLM 5.3 Flash
GLM · batiai
Params313B
Context1024K
Q4_K_M188.7 GB
GGUF
QW
Qwen3.8 Flash Next
Qwen · batiai
Params177B
Context256K
Q4_K_M119.2 GB
GGUF
GE
Google Gemma 4 26B A4B It
Gemma · batiai
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
QW
Qwen Qwen3 VL Embedding 8B
Qwen · batiai
Params7.57B
Context256K
Smallest6.2 GB
EmbeddingTool useVision
GE
Google Gemma 4 E4B It
Gemma · batiai
Params7.5B
Context128K
Q4_K_M5.3 GB
Vision
GE
Google Gemma 4 12B It
Gemma · batiai
Params11.9B
Context256K
Q4_K_M7.4 GB
CodingReasoningTool use
FA
Microsoft Fara 7B
Fara · batiai
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QW
Qwen Qwen3 Reranker 8B
Qwen · batiai
Params7.57B
Context40K
Smallest6.2 GB
EmbeddingReasoningTool use
GE
Google Gemma 4 E2B It
Gemma · batiai
Params4.65B
Context128K
Q4_K_M3.4 GB
Vision
GE
Google Gemma 4 31B It
Gemma · batiai
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningTool useVision
UN
batisee
Unlimited · batiai
Params2.93B
Context32K
Q4_K_M2.0 GB
GGUF
QW
Qwen Qwen3.5 9B
Qwen · batiai
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
LL
Meta Llama Llama 4 Scout 17B 16E Instruct
Llama · batiai
Params108B
Context10240K
Q4_K_M40.2 GB
Tool useVision
QW
Qwen Qwen3 Embedding 8B
Qwen · batiai
Params7.57B
Context40K
Smallest6.2 GB
EmbeddingTool use
QW
Qwen Qwen3 VL Embedding 2B
Qwen · batiai
Params1.72B
Context256K
Smallest1.4 GB
EmbeddingTool useVision
NE
Nemotron 3 Nano Omni 30B Text Only
Nemotron · batiai
Params31.6B
Context1024K
Smallest17.9 GB
ReasoningTool use
LF
LiquidAI LFM2.5 8B A1B
Lfm · batiai
Params8.47B
Context125K
Q4_K_M5.2 GB
ReasoningTool use
QW
Qwen Qwen3 Embedding 0.6B
Qwen · batiai
Params596M
Context32K
Smallest0.5 GB
EmbeddingReasoningTool use
MI
Mistral Small 4 119B 2603
Mistral · batiai
Params119B
Context1024K
Q4_K_M72.2 GB
Reasoning
GR
Gravity 30BA5B RL
Gravity · batiai
Params29.6B
Context128K
Q4_K_M19.6 GB
ReasoningTool use
QW
Qwen Qwen3 Embedding 4B
Qwen · batiai
Params4.02B
Context40K
Smallest3.3 GB
EmbeddingTool use
GR
Ibm Granite Granite 4.1 8b
Granite · batiai
Params8.79B
Context128K
Q4_K_M5.3 GB
Tool use
QW
Qwen Qwen3.5 35B A3B
Qwen · batiai
Params34.7B
Context256K
Smallest18.7 GB
ReasoningTool use
GL
GLM 5.2 Safetensors
GLM · batiai
Params753B
Context1024K
Smallest230.0 GB
GGUF
QW
Qwen Qwen3 Reranker 0.6B
Qwen · batiai
Params596M
Context40K
Smallest0.5 GB
EmbeddingReasoningTool use
HY
Hy3
batiai
Params295B
Context256K
Q4_K_M178.6 GB
GGUF
QW
Qwen Qwen3 Reranker 4B
Qwen · batiai
Params4.02B
Context40K
Smallest3.3 GB
EmbeddingReasoningTool use

About batiai on Hugging Face

batiai has published 39 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Nemotron. The most downloaded are Qwen Qwen3.6 27B, Qwen3.8 27B and Qwen Qwen3.6 35B A3B.

The quants batiai publishes most often are Q6_K (23), Q4_K_M (20), IQ4_XS (19) and IQ3_XXS (18). Their Q4_K_M files range from 2.0 to 951.2 GB. Parameter counts run from 596M to 1570B, and the longest trained context window is 10240K tokens.

Frequently asked questions

What GGUF models has batiai published?

39 models are listed here, mainly from the Qwen, Gemma and Nemotron families. The most downloaded is Qwen Qwen3.6 27B.

Which quants does batiai publish?

The most common are Q6_K (23 models), Q4_K_M (20 models), IQ4_XS (19 models) and IQ3_XXS (18 models).

Keep browsing