GGUF models by qwp4w3hyb

67 GGUF models quantized by qwp4w3hyb on Hugging Face. Sizes run from 1B to 236B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Meta-Llama-3-8B-Instruct
Llama · qwp4w3hyb
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
ST
Starling LM 7B beta iMat
Starling · qwp4w3hyb
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
CO
c4ai-command-r-v01
Command R · qwp4w3hyb
Params35B
Context128K
Q4_K_M21.5 GB
GGUF
PH
Phi 3 mini 4k instruct iMat
Phi · qwp4w3hyb
Params3.82B
Context4K
Q4_K_M2.4 GB
Coding
GE
gemma-2-27b-it
Gemma · qwp4w3hyb
Params27.2B
Context8K
Smallest6.1 GB
GGUF
GE
gemma-2-9b-it
Gemma · qwp4w3hyb
Params9.24B
Context8K
Smallest2.4 GB
GGUF
LL
Meta Llama 3.1 70B Instruct
Llama · qwp4w3hyb
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
MI
Hermes 2 Pro Mistral 7B iMat
Mistral · qwp4w3hyb
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
PH
Phi 3 mini 128k instruct iMat
Phi · qwp4w3hyb
Params3.82B
Context128K
Q4_K_M2.4 GB
Coding
MI
Nous Hermes 2 Mixtral 8x7B DPO iMat
Mistral · qwp4w3hyb
Params46.7B
Context32K
Q4_K_M28.4 GB
Tool use
DE
deepseek-coder-7b-instruct-v1.5
DeepSeek · qwp4w3hyb
Params6.91B
Context4K
Q4_K_M4.2 GB
Coding
LL
Llama-3-8B-Instruct-Gradient-1048k
Llama · qwp4w3hyb
Params8.03B
Context1024K
Q4_K_M4.9 GB
GGUF
LL
Meta-Llama-3-70B-Instruct
Llama · qwp4w3hyb
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
MI
Mistral Nemo Instruct 2407
Mistral · qwp4w3hyb
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
WI
WizardLM-2-8x22B
Wizardlm · qwp4w3hyb
Params141B
Context64K
Q4_K_M85.6 GB
GGUF
NO
Nous Hermes 2 SOLAR 10.7B iMat
Nous · qwp4w3hyb
Params10.7B
Context4K
Q4_K_M6.5 GB
Tool use
QW
Replete-Coder-Qwen2-1.5b
Qwen · qwp4w3hyb
Params1.54B
Context128K
Q4_K_M1.0 GB
CodingTool use
MI
Codestral 22B v0.1 iMat
Mistral · qwp4w3hyb
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
YI
Yi-1.5-9B-Chat
Yi · qwp4w3hyb
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
CO
c4ai-command-r-plus
Command R · qwp4w3hyb
Params104B
Context128K
Q4_K_M62.8 GB
GGUF
GE
Gemma 3 27b It
Gemma · qwp4w3hyb
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · qwp4w3hyb
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
MI
Not WizardLM 2 7B iMat
Microsoft · qwp4w3hyb
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
PH
Phi 3 medium 128k instruct iMat
Phi · qwp4w3hyb
Params14B
Context128K
Q4_K_M8.6 GB
Coding
HU
Hunyuan A13B Instruct Hf
Hunyuan · qwp4w3hyb
Params80.4B
Context256K
Q4_K_M48.8 GB
ReasoningTool use
QW
Qwen2-7B-Instruct
Qwen · qwp4w3hyb
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
Qwen1.5 32B Chat iMat
Qwen · qwp4w3hyb
Params32.5B
Context32K
Q4_K_M19.7 GB
GGUF
YI
Nous Hermes 2 Yi 34B iMat
Yi · qwp4w3hyb
Params34.4B
Context4K
Q4_K_M20.7 GB
Tool use
QW
Qwen1.5 MoE A2.7B Chat iMat
Qwen · qwp4w3hyb
Params14.3B
Context32K
Q4_K_M9.5 GB
GGUF
QW
Qwen2-72B-Instruct
Qwen · qwp4w3hyb
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF

About qwp4w3hyb on Hugging Face

qwp4w3hyb has published 67 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Mistral. The most downloaded are Meta-Llama-3-8B-Instruct, Starling LM 7B beta iMat and c4ai-command-r-v01.

The quants qwp4w3hyb publishes most often are IQ4_XS (66), IQ1_S (65), Q6_K (62) and Q4_K_M (62). Their Q4_K_M files range from 0.8 to 85.6 GB. Parameter counts run from 1B to 236B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has qwp4w3hyb published?

67 models are listed here, mainly from the Llama, Qwen and Mistral families. The most downloaded is Meta-Llama-3-8B-Instruct.

Which quants does qwp4w3hyb publish?

The most common are IQ4_XS (66 models), IQ1_S (65 models), Q6_K (62 models) and Q4_K_M (62 models).

Keep browsing