GGUF models by SinpxAI

50 GGUF models quantized by SinpxAI on Hugging Face. Sizes run from 1.1B to 7.51B parameters. The longest trained context is 195K tokens.

Most downloadedNewestLargestLongest contextSmallest
OP
OpenZephyrChat
Openzephyrchat · SinpxAI
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NE
Neural Chat 7B v3.2
Neural · SinpxAI
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OP
OpenChat 3.5 7B Solar
Openchat · SinpxAI
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
OP
OpenChat 3.5 0106
Openchat · SinpxAI
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
MI
OpenBuddy Mistral 7B v13 Base
Mistral · SinpxAI
Params7.28B
Context32K
Q4_K_M4.4 GB
GGUF
OP
OpenZephyrChat v0.2
Openzephyrchat · SinpxAI
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
NeuralHermes Mistral 7B v2.5
Mistral · SinpxAI
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
BA
Baichuan2 7B Chat
Baichuan · SinpxAI
Params7.51B
Context4K
Q4_K_M4.6 GB
GGUF
YI
Yi 6B
Yi · SinpxAI
Params6.06B
Context4K
Q4_K_M3.7 GB
GGUF
ZE
Zephyr 7B beta
Zephyr · SinpxAI
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
OpenBuddy Mistral 7B v13.1
Mistral · SinpxAI
Params7.28B
Context32K
Q4_K_M4.4 GB
GGUF
ST
Starling LM 7B beta
Starling · SinpxAI
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
OP
OpenOrca Zephyr 7B
Openorca · SinpxAI
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Mistral 7B Instruct v0.2 code ft
Mistral · SinpxAI
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
MI
OpenHermes 2 Mistral 7B
Mistral · SinpxAI
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
MI
OpenBuddy Mistral 7B v13
Mistral · SinpxAI
Params7.28B
Context32K
Q4_K_M4.4 GB
GGUF
VI
Vicuna 7B v1.5
Vicuna · SinpxAI
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
MI
OpenHermes 2.5 Mistral 7B
Mistral · SinpxAI
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
MI
Mistral 7B v0.1
Mistral · SinpxAI
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
VI
Vicuna 7B v1.3
Vicuna · SinpxAI
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF

Keep browsing