GGUF models by duyntnet
305 GGUF models quantized by duyntnet on Hugging Face. Sizes run from 163M to 35B parameters. The longest trained context is 1024K tokens.
MP
mpt-7b-storywriter
Mpt · duyntnet
Params6.65B
Context64K
Q4_K_M4.3 GB
LL
Asclepius-Llama2-13B
Llama · duyntnet
Params13B
Context4K
Q4_K_M7.9 GB
SU
SuperNova Medius
Supernova · duyntnet
Params14.8B
Context128K
Q4_K_M9.0 GB
LE
Lelemon Maid 7B
Lelemon · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
HX-Mistral-3B_v0.1
Mistral · duyntnet
Params3.75B
Context32K
Q4_K_M2.3 GB
MY
Mythomist 7b
Mythomist · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
MA
Magro 7b v1.1 imatrix
Magro · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen3 32B
Qwen · duyntnet
Params32.8B
Context40K
Q4_K_M19.8 GB
QW
Qwen1.5-7B-Chat
Qwen · duyntnet
Params7.72B
Context32K
Q4_K_M4.8 GB
VI
vicuna 7b v1.5 imatrix
Vicuna · duyntnet
Params6.74B
Context4K
Q4_K_M4.1 GB
OC
Octopus-v2
Octopus · duyntnet
Params2.51B
Context8K
Q4_K_M1.6 GB
RE
ReMask-3B
Remask · duyntnet
Params2.8B
Context4K
Q4_K_M1.7 GB
GE
Gemma 3 Glitter 12B
Gemma · duyntnet
Params11.8B
Context128K
Q4_K_M7.3 GB
MI
Mistral-7B-Instruct-v0.2
Mistral · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen2.5 Coder 1.5B
Qwen · duyntnet
Params1.54B
Context32K
Q4_K_M1.0 GB
LL
Llama 3.2 3B
Llama · duyntnet
Params3.21B
Context128K
Q4_K_M2.0 GB
MI
Mistral Small Instruct 2409
Mistral · duyntnet
Params22.2B
Context32K
Q4_K_M13.3 GB
UI
UIGEN X 4B 0729
Uigen · duyntnet
Params4.41B
Context40K
Q4_K_M2.7 GB
NX
Nxcode CQ 7B Orpo
Nxcode · duyntnet
Params7.25B
Context64K
Q4_K_M4.7 GB
GE
Gemma 2 Ifable 9B
Gemma · duyntnet
Params9.24B
Context8K
Q4_K_M5.8 GB
LL
DeepHermes 3 Llama 3 8B Preview imatrix
Llama · duyntnet
Params8.03B
Context128K
Q4_K_M4.9 GB
SE
Seed Coder 8B Instruct
Seed · duyntnet
Params8.25B
Context32K
Q4_K_M5.1 GB
QW
Qwen2.5 Coder 14B Instruct
Qwen · duyntnet
Params14.8B
Context32K
Q4_K_M9.0 GB
AY
aya-23-8B
Aya · duyntnet
Params8.03B
Context8K
Q4_K_M5.1 GB
MY
mythalion-13b
Mythalion · duyntnet
Params13B
Context4K
Q4_K_M7.9 GB
CO
CodeQwen1.5-7B
Codeqwen · duyntnet
Params7.25B
Context64K
Q4_K_M4.7 GB
DE
deepseek-coder-7b-instruct-v1.5
DeepSeek · duyntnet
Params6.91B
Context4K
Q4_K_M4.2 GB
IN
InternLM2
InternLM · duyntnet
Params7.74B
Context32K
Q4_K_M4.7 GB
MP
mpt-7b-8k-chat
Mpt · duyntnet
Params6.65B
Context8K
Q4_K_M4.3 GB
AE
Aethora 7b v1 imatrix
Aethora · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB