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
QW
Qwen2.5 32B Instruct
Qwen · grapevine-AI
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
CO
c4ai command r v01
Command R · grapevine-AI
Params35B
Context128K
Q4_K_M21.5 GB
GGUF
QW
Qwen2.5 Bakeneko 32b Instruct v2
Qwen · grapevine-AI
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
MI
Mistral Small 24B Instruct 2501
Mistral · grapevine-AI
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
QW
Qwq Bakeneko 32b
Qwen · grapevine-AI
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
PH
Phi 4 Open R1 Distill EZOv1
Phi · grapevine-AI
Params14.7B
Context16K
Q4_K_M9.1 GB
Reasoning
CO
C4Ai Command R Plus 08 2024
Command R · grapevine-AI
Params104B
Context128K
Q4_K_M62.8 GB
GGUF
LL
Meta Llama 3.1 70B Instruct
Llama · grapevine-AI
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
QW
qwen2.5-72b-instruct
Qwen · grapevine-AI
Params73B
Context32K
Q4_K_M44.0 GB
Tool use
DE
Deepseek R1 Distill Qwen2.5 Bakeneko 32b
DeepSeek · grapevine-AI
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
QW
ABEJA Qwen2.5 32b Japanese v0.1
Qwen · grapevine-AI
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
ST
stockmark 100b instruct v0.1
Stockmark · grapevine-AI
Params96.2B
Context4K
Q4_K_M57.7 GB
GGUF
MI
Mistral Small 24B Instruct 2501
Mistral · grapevine-AI
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
DE
Phi 4 Deepseek R1K RL EZO
DeepSeek · grapevine-AI
Params14.7B
Context16K
Q4_K_M9.1 GB
GGUF
LL
Athene 70B
Llama · grapevine-AI
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
SA
Sarashina2 70b
Sarashina · grapevine-AI
Params70.1B
Context8K
Q4_K_M42.2 GB
GGUF
AR
Arcee Blitz
Arcee · grapevine-AI
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF

Keep browsing