GGUF models by nold

43 GGUF models quantized by nold on Hugging Face. Sizes run from 1.35B to 46.7B parameters. The longest trained context is 512K tokens.

Most downloadedNewestLargestLongest contextSmallest
PH
Phi 3 mini 4k instruct function calling
Phi · nold
Params3.82B
Context4K
Q4_K_M2.4 GB
Tool use
CR
CroissantLLMChat v0.1
Croissantllmchat · nold
Params1.35B
Context2K
Q4_K_M0.9 GB
Coding
MI
Mistral 7B Instruct v0.2 Neural Story
Mistral · nold
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
vietnamese llama2 7b 120GB
Llama · nold
Params6.85B
Context2K
Q4_K_M4.2 GB
GGUF
ST
starcoder2 7b
StarCoder · nold
Params7.17B
Context16K
Q4_K_M4.4 GB
Coding
GE
gemma 2b
Gemma · nold
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
HE
HelpingAI 9B
Helpingai · nold
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
MI
OpenMath Mistral 7B v0.1 hf
Mistral · nold
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
ST
starcoder2 15b
StarCoder · nold
Params16B
Context16K
Q4_K_M9.9 GB
Coding
ST
starcoder2 3b
StarCoder · nold
Params3.03B
Context16K
Q4_K_M1.8 GB
Coding
MI
ChatHercules 2.5 Mistral 7B
Mistral · nold
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BA
Smaug 34B v0.1
Bagel · nold
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
OR
Orion 14B Base
Orion · nold
Params14.5B
Context4K
Q4_K_M8.8 GB
Coding
YI
Yi 34B 200K RPMerge
Yi · nold
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
BR
Breeze 7B Instruct v1 0
Breeze · nold
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
WS
WSB GPT 7B
Wsb · nold
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
MI
merlinite 7b
Mistral · nold
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GE
openbuddy gemma 7b v19.1 4k
Gemma · nold
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
GO
gorilla openfunctions v2
Gorilla · nold
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
BI
BioMistral 7B
Biomistral · nold
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GE
SauerkrautLM Gemma 7b
Gemma · nold
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
YI
Yi 34B 200K
Yi · nold
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
RE
Reyna Mini 1.8B v0.1
Reyna · nold
Params1.84B
Context32K
Q4_K_M1.2 GB
CodingTool use
IN
InternLM2
InternLM · nold
Params19.9B
Context32K
Q4_K_M12.0 GB
GGUF
MI
Einstein v4 7B
Mistral · nold
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingTool use
CO
c4ai command r v01
Command R · nold
Params35B
Context128K
Q4_K_M21.5 GB
GGUF
LU
Lumosia v2 MoE 4x10.7
Lumosia · nold
Params36.1B
Context4K
Q4_K_M21.8 GB
GGUF
LL
LLaMAntino 2 13b hf ITA
Llama · nold
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
MI
openbuddy-mixtral-7bx8-v18.1-32k
Mistral · nold
Params46.7B
Context32K
Q4_K_M28.5 GB
GGUF
MI
OpenHermes Emojitron 001
Mistral · nold
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use

About nold on Hugging Face

nold has published 43 GGUF models that ggufmodels.com tracks, across families such as Mistral, StarCoder and Gemma. The most downloaded are Phi 3 mini 4k instruct function calling, CroissantLLMChat v0.1 and Mistral 7B Instruct v0.2 Neural Story.

The quants nold publishes most often are Q8_0 (43), Q5_K_M (42), Q4_K_M (42) and Q6_K (36). Their Q4_K_M files range from 0.9 to 28.5 GB. Parameter counts run from 1.35B to 46.7B, and the longest trained context window is 512K tokens.

Frequently asked questions

What GGUF models has nold published?

43 models are listed here, mainly from the Mistral, StarCoder and Gemma families. The most downloaded is Phi 3 mini 4k instruct function calling.

Which quants does nold publish?

The most common are Q8_0 (43 models), Q5_K_M (42 models), Q4_K_M (42 models) and Q6_K (36 models).

Keep browsing