GGUF models by smarttasks

36 GGUF models quantized by smarttasks on Hugging Face. Sizes run from 23M to 30.5B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen_Qwen2.5 Coder 7B Instruct
Qwen · smarttasks
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
QW
Qwen_Qwen3 Coder 30B A3B Instruct
Qwen · smarttasks
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
QW
Qwen_Qwen2.5 Coder 14B Instruct
Qwen · smarttasks
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
BG
bge reranker v2 m3
BGE · smarttasks
Params568M
Context8K
Q4_K_M0.4 GB
CodingEmbedding
BG
bge m3
BGE · smarttasks
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
PH
Phi Mini MoE
Phi · smarttasks
Params7.65B
Context4K
Q4_K_M5.0 GB
GGUF
QW
Qwen3 Embedding 0.6B
Qwen · smarttasks
Params596M
Context32K
Q4_K_M0.4 GB
EmbeddingReasoningTool use
SM
HuggingFaceTB_SmolLM3 3B
SmolLM · smarttasks
Params3.08B
Context64K
Q4_K_M1.9 GB
ReasoningTool use
MI
mistralai_Mistral Small 3.2 24B Instruct 2506
Mistral · smarttasks
Params23.6B
Context128K
Q4_K_M14.3 GB
Tool use
QW
Qwen_Qwen3 1.7B
Qwen · smarttasks
Params2.03B
Context40K
Q4_K_M1.3 GB
ReasoningTool use
QW
Qwen_Qwen3 8B
Qwen · smarttasks
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
BG
Bge Small En v1.5
BGE · smarttasks
Params33M
Context512
Q4_K_M0.0 GB
Embedding
DE
Deepseek ai_DeepSeek R1 Distill Qwen 7B
DeepSeek · smarttasks
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
CO
01 ai_Yi Coder 9B Chat
Coder · smarttasks
Params8.83B
Context128K
Q4_K_M5.3 GB
CodingTool use
FA
tiiuae_Falcon3 10B Instruct
Falcon · smarttasks
Params10.3B
Context32K
Q4_K_M6.3 GB
Tool use
PH
phi 4
Phi · smarttasks
Params14.7B
Context16K
Q4_K_M9.1 GB
Tool use
GE
React Agent Coder Gemma 4 E4B
Gemma · smarttasks
Params7.52B
Context128K
Q4_K_M5.3 GB
CodingReasoningTool use
QW
Qwen_Qwen3 14B
Qwen · smarttasks
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
GE
Google_Gemma 4 12b It
Gemma · smarttasks
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool use
QW
Qwen_Qwen3.6 27B
Qwen · smarttasks
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
SA
Sarvamai_Sarvam M
Sarvam · smarttasks
Params23.6B
Context32K
Q4_K_M14.3 GB
ReasoningTool use
GP
Openai_Gpt Oss 20b
gpt-oss · smarttasks
Params20.9B
Context128K
Smallest13.8 GB
Tool use
LL
React Agent Coder Llama 3.1 8b
Llama · smarttasks
Params8.03B
Context128K
Q4_K_M4.9 GB
CodingTool use
GR
Ibm Granite_Granite 3.3 8b Instruct
Granite · smarttasks
Params8.17B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
QW
Qwen_Qwen3 4B
Qwen · smarttasks
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen_Qwen3 0.6B
Qwen · smarttasks
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
LL
Meta llama_Llama 3.2 3B Instruct
Llama · smarttasks
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
NO
Nomic Embed Text v1.5
Nomic · smarttasks
Params137M
Context2K
Q4_K_M0.1 GB
Embedding
AL
all MiniLM L6 v2
All · smarttasks
Params23M
Context512
Q4_K_M0.0 GB
Embedding
MU
Muse Glimmer 30b
Muse · smarttasks
Params27.9B
Context128K
Smallest19.8 GB
ReasoningTool use

About smarttasks on Hugging Face

smarttasks has published 36 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and BGE. The most downloaded are Qwen_Qwen2.5 Coder 7B Instruct, Qwen_Qwen3 Coder 30B A3B Instruct and Qwen_Qwen2.5 Coder 14B Instruct.

The quants smarttasks publishes most often are Q8_0 (34), Q5_K_M (34), Q4_K_M (34) and Q6_K (25). Their Q4_K_M files range from 0.0 to 18.6 GB. Parameter counts run from 23M to 30.5B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has smarttasks published?

36 models are listed here, mainly from the Qwen, Gemma and BGE families. The most downloaded is Qwen_Qwen2.5 Coder 7B Instruct.

Which quants does smarttasks publish?

The most common are Q8_0 (34 models), Q5_K_M (34 models), Q4_K_M (34 models) and Q6_K (25 models).

Keep browsing