GGUF models by dispatchAI

36 GGUF models quantized by dispatchAI on Hugging Face. Sizes run from 135M to 7.62B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
Gemma 2B Arabic mobile
Gemma · dispatchAI
Params2.51B
Context8K
Smallest1.6 GB
GGUF
QW
qwen2.5-1.5b-instruct
Qwen · dispatchAI
Params1.78B
Context32K
Smallest1.1 GB
Tool use
LL
Llama 3.2 3B Instruct
Llama · dispatchAI
Params3.21B
Context128K
Smallest2.0 GB
Tool use
LL
Llama 3.2 1B Instruct
Llama · dispatchAI
Params1.24B
Context128K
Smallest1.0 GB
Tool use
QW
Qwen2.5 0.5B Instruct
Qwen · dispatchAI
Params494M
Context32K
Smallest0.5 GB
Tool use
QW
Qwen2.5 Coder 1.5B mobile
Qwen · dispatchAI
Params1.54B
Context32K
Smallest1.0 GB
CodingTool use
EM
Embeddinggemma 300m
Embeddinggemma · dispatchAI
Params308M
Context2K
Smallest0.3 GB
Embedding
LL
Llama 3.2 3B FunctionCall mobile
Llama · dispatchAI
Params3.21B
Context1024K
Smallest2.0 GB
Tool use
TI
TinyLlama 1.1B Chat Q5 mobile
Tinyllama · dispatchAI
Params1.1B
Context2K
Smallest0.8 GB
GGUF
QW
Qwen2.5 1.5B Instruct
Qwen · dispatchAI
Params1.54B
Context32K
Smallest1.1 GB
Tool use
QW
qwen2.5-0.5b-instruct
Qwen · dispatchAI
Params630M
Context32K
Smallest0.5 GB
CodingTool use
WH
Whisper Small ASR mobile
Whisper · dispatchAI
Params242M
Context—
Smallest0.3 GB
GGUF
MI
MiniCPM5 1B
MiniCPM · dispatchAI
Params1.08B
Context128K
Smallest0.7 GB
ReasoningTool use
QW
Qwen2.5 Coder 7B mobile
Qwen · dispatchAI
Params7.62B
Context32K
Smallest4.7 GB
CodingTool use
QW
Qwen2.5 1.5B Instruct
Qwen · dispatchAI
Params1.54B
Context32K
Smallest1.6 GB
Tool use
QW
Qwen2.5 Math 1.5B mobile
Qwen · dispatchAI
Params1.54B
Context4K
Smallest1.0 GB
Tool use
LL
Llama 3.2 1B Instruct
Llama · dispatchAI
Params1.24B
Context128K
Smallest0.8 GB
Tool use
MI
MiniCPM V 4_6
MiniCPM · dispatchAI
Params752M
Context256K
Smallest0.5 GB
ReasoningTool useVision
SM
SmolLM2 135M Instruct
SmolLM · dispatchAI
Params135M
Context8K
Smallest0.1 GB
GGUF
GE
Gemma 2 2b It
Gemma · dispatchAI
Params2.61B
Context8K
Smallest1.7 GB
GGUF
LL
Llama 3.2 1B FunctionCall mobile
Llama · dispatchAI
Params3.21B
Context1024K
Smallest2.0 GB
Tool use
LL
Llama 3.2 1B Instruct
Llama · dispatchAI
Params1.24B
Context128K
Smallest1.3 GB
GGUF
GE
Gemma 2 2b It
Gemma · dispatchAI
Params2.61B
Context8K
Smallest1.9 GB
GGUF
QW
Qwen2.5 0.5B Chinese mobile
Qwen · dispatchAI
Params494M
Context32K
Smallest0.4 GB
Tool use
LL
Llama 3.2 3B Instruct
Llama · dispatchAI
Params3.21B
Context128K
Smallest2.3 GB
Tool use
SM
SmolLM2 360M Instruct
SmolLM · dispatchAI
Params362M
Context8K
Smallest0.3 GB
GGUF
QW
Qwen3 Embedding 0.6b
Qwen · dispatchAI
Params596M
Context32K
Smallest0.6 GB
EmbeddingReasoningTool use
QW
Qwen2.5 0.5B Coder mobile
Qwen · dispatchAI
Params494M
Context32K
Smallest0.4 GB
CodingTool use
EM
Embeddinggemma 300m
Embeddinggemma · dispatchAI
Params308M
Context2K
Smallest0.3 GB
Embedding
PH
Phi 3.5 Mini Instruct
Phi · dispatchAI
Params3.82B
Context128K
Smallest2.4 GB
GGUF

About dispatchAI on Hugging Face

dispatchAI has published 36 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and SmolLM. The most downloaded are Gemma 2B Arabic mobile, qwen2.5-1.5b-instruct and Llama 3.2 3B Instruct.

Parameter counts run from 135M to 7.62B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has dispatchAI published?

36 models are listed here, mainly from the Qwen, Llama and SmolLM families. The most downloaded is Gemma 2B Arabic mobile.

Which quants does dispatchAI publish?

See the model pages for the exact list of files.

Keep browsing