GGUF models by grapevine-AI

77 GGUF models quantized by grapevine-AI on Hugging Face. Sizes run from 494M to 111B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
CA
calm3-22b-chat
Calm · grapevine-AI
Params22.5B
Context16K
Q4_K_M13.6 GB
GGUF
GE
Gemma 2 27b It
Gemma · grapevine-AI
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
MI
Mistral Nemo Instruct 2407
Mistral · grapevine-AI
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
GE
Gemma 3n E4B It
Gemma · grapevine-AI
Params6.87B
Context32K
Q4_K_M4.2 GB
GGUF
QW
Qwen3 30B A3B Instruct 2507
Qwen · grapevine-AI
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningTool use
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · grapevine-AI
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingTool use
QW
Qwen3 Coder 30B A3B Instruct
Qwen · grapevine-AI
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
LL
Meta-Llama-3-70B-Instruct
Llama · grapevine-AI
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
PL
Plamo 2 Translate
Plamo · grapevine-AI
Params9.53B
Context10240K
Q4_K_M5.8 GB
GGUF
QW
Qwen3 30B A3B Thinking 2507
Qwen · grapevine-AI
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningTool use
GE
Gemma 2 2b Jpn It
Gemma · grapevine-AI
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
LL
Llama 3.2 3B Instruct
Llama · grapevine-AI
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
QW
Qwen2.5 Coder 0.5B Instruct
Qwen · grapevine-AI
Params494M
Context32K
Q4_K_M0.4 GB
CodingTool use
GE
Gemma 3 12b It
Gemma · grapevine-AI
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
MI
Codestral 22B v0.1
Mistral · grapevine-AI
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
QW
ABEJA QwQ32b Reasoning Japanese v1.0
Qwen · grapevine-AI
Params32.8B
Context32K
Q4_K_M19.9 GB
ReasoningTool use
RA
RakutenAI 2.0 8x7B Instruct
Rakutenai · grapevine-AI
Params46.8B
Context32K
Q4_K_M28.5 GB
GGUF
QW
Qwen3 32B
Qwen · grapevine-AI
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
QW
Qwen2-57B-A14B-Instruct
Qwen · grapevine-AI
Params57.4B
Context32K
Q4_K_M34.9 GB
GGUF
QW
Qwen2.5 Coder 32B Instruct
Qwen · grapevine-AI
Params32.8B
Context32K
Q4_K_M19.9 GB
CodingTool use
GE
Gemma 3 27b It
Gemma · grapevine-AI
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
DE
DeepSeek R1 Distill Qwen 32B Japanese
DeepSeek · grapevine-AI
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
QW
QwQ 32B Preview
Qwen · grapevine-AI
Params32.8B
Context32K
Q4_K_M19.9 GB
ReasoningTool use
QW
qwen2.5-32b-instruct
Qwen · grapevine-AI
Params32.8B
Context128K
Q4_K_M19.9 GB
Tool use
LL
Llama 3.2 1B Instruct
Llama · grapevine-AI
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
DE
DeepSeek R1 0528 Qwen3 8B
DeepSeek · grapevine-AI
Params8.19B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
GE
EZO Humanities 9B gemma 2 it
Gemma · grapevine-AI
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
QW
Qwen3 30B A3B
Qwen · grapevine-AI
Params30.5B
Context40K
Q4_K_M18.6 GB
ReasoningTool use
QW
Qwen2-72B-Instruct
Qwen · grapevine-AI
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
CO
c4ai-command-r-plus
Command R · grapevine-AI
Params104B
Context128K
Q4_K_M62.8 GB
GGUF

About grapevine-AI on Hugging Face

grapevine-AI has published 77 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Gemma. The most downloaded are calm3-22b-chat, Gemma 2 27b It and Mistral Nemo Instruct 2407.

The quants grapevine-AI publishes most often are Q4_K_M (77), BF16 (65), IQ4_XS (51) and Q5_K_M (37). Their Q4_K_M files range from 0.4 to 67.1 GB. Parameter counts run from 494M to 111B, and the longest trained context window is 10240K tokens.

Frequently asked questions

What GGUF models has grapevine-AI published?

77 models are listed here, mainly from the Qwen, Llama and Gemma families. The most downloaded is calm3-22b-chat.

Which quants does grapevine-AI publish?

The most common are Q4_K_M (77 models), BF16 (65 models), IQ4_XS (51 models) and Q5_K_M (37 models).

Keep browsing