GGUF models by enacimie

84 GGUF models quantized by enacimie on Hugging Face. Sizes run from 23M to 34.7B parameters. The longest trained context is 986K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3 4B
Qwen · enacimie
Params4.02B
Context40K
Q4_K_M5.0 GB
GGUF
QW
Qwen2.5 1.5B Instruct
Qwen · enacimie
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
QW
Qwen3 1.7B
Qwen · enacimie
Params2.03B
Context40K
Q4_K_M2.6 GB
ReasoningTool use
QW
Qwen3 0.6B
Qwen · enacimie
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
QW
Qwen3 Embedding 0.6B
Qwen · enacimie
Params596M
Context32K
Q4_K_M0.4 GB
EmbeddingReasoningTool use
QW
Qwen3 8B
Qwen · enacimie
Params8.19B
Context40K
Q4_K_M10.1 GB
ReasoningTool use
QW
Qwen3 30B A3B
Qwen · enacimie
Params30.5B
Context40K
Q4_K_M37.1 GB
ReasoningTool use
QW
Qwen3 Embedding 4B
Qwen · enacimie
Params4.02B
Context40K
Q4_K_M2.5 GB
EmbeddingTool use
QW
Qwen3.5 4B
Qwen · enacimie
Params4.33B
Context256K
Q4_K_M2.8 GB
ReasoningTool useVision
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · enacimie
Params1.78B
Context128K
Q4_K_M2.2 GB
ReasoningTool use
MA
Madlad400 3b Mt
Madlad · enacimie
Params2.94B
Context512
Q4_K_M1.9 GB
GGUF
WE
WebSailor 3B
Websailor · enacimie
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
QW
Qwen2.5 VL 3B Instruct
Qwen · enacimie
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
QW
Qwen3.5 9B
Qwen · enacimie
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
MA
Madlad400 7b Mt
Madlad · enacimie
Params8.3B
Context512
Q4_K_M5.2 GB
GGUF
LF
LFM2 700M
Lfm · enacimie
Params742M
Context125K
Q4_K_M0.5 GB
GGUF
QW
Qwen3.6 35B A3B
Qwen · enacimie
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
SM
SmolLM3 3B
SmolLM · enacimie
Params3.08B
Context64K
Q4_K_M1.9 GB
GGUF
QW
Qwen3 Embedding 8B
Qwen · enacimie
Params7.57B
Context40K
Q4_K_M4.7 GB
EmbeddingTool use
TA
UI TARS 2B SFT
Tars · enacimie
Params1.78B
Context32K
Q4_K_M2.2 GB
Vision
QW
Qwen3.5 2B
Qwen · enacimie
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
DE
DeepSeek R1 0528 Qwen3 8B
DeepSeek · enacimie
Params8.19B
Context128K
Q4_K_M10.1 GB
ReasoningTool use
QW
Qwen3 4B
Qwen · enacimie
Params4.02B
Context40K
Smallest4.3 GB
ReasoningTool use
LF
LFM2 1.2B
Lfm · enacimie
Params1.17B
Context125K
Q4_K_M0.7 GB
GGUF
OV
OvisOCR2
Ovisocr · enacimie
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · enacimie
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
GP
gpt2 Q4 K M
Gpt · enacimie
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
QW
Qwen3 Reranker 4B
Qwen · enacimie
Params4.02B
Context40K
Smallest4.3 GB
EmbeddingReasoningTool use
QW
Qwen3 VL 2B Instruct
Qwen · enacimie
Params1.72B
Context256K
Smallest0.8 GB
Tool useVision
QW
Qwen3 1.7B
Qwen · enacimie
Params2.03B
Context40K
Smallest2.2 GB
ReasoningTool use

About enacimie on Hugging Face

enacimie has published 84 GGUF models that ggufmodels.com tracks, across families such as Qwen, Ernie and DeepSeek. The most downloaded are Qwen3 4B, Qwen2.5 1.5B Instruct and Qwen3 1.7B.

The quants enacimie publishes most often are Q4_K_M (56), Q8_0 (12), Q2_K (9) and Q3_K_M (3). Their Q4_K_M files range from 0.0 to 37.1 GB. Parameter counts run from 23M to 34.7B, and the longest trained context window is 986K tokens.

Frequently asked questions

What GGUF models has enacimie published?

84 models are listed here, mainly from the Qwen, Ernie and DeepSeek families. The most downloaded is Qwen3 4B.

Which quants does enacimie publish?

The most common are Q4_K_M (56 models), Q8_0 (12 models), Q2_K (9 models) and Q3_K_M (3 models).

Keep browsing