GGUF models by RichardErkhov

14354 GGUF models quantized by RichardErkhov on Hugging Face. Sizes run from 1M to 316B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
ibivibiv Llama 3 2B Instruct QuarterWit
Llama · RichardErkhov
Params2.8B
Context8K
Q4_K_M1.8 GB
GGUF
LL
uukuguy speechless codellama orca airoboros 13b 0.10e
Llama · RichardErkhov
Params410M
Context—
Q4_K_M2.5 GB
Coding
MI
ewqr2130 mistral inst v02 dpo
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
mlfoundations dev mistral 7b 0 3 oh dcft v3.1 llama 3.3 70b
Llama · RichardErkhov
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
QW
VanillaKD Pretrain Qwen 500M
Qwen · RichardErkhov
Params464M
Context32K
Q4_K_M0.3 GB
GGUF
LL
codellama CodeLlama 13b hf
Llama · RichardErkhov
Params13B
Context16K
Q4_K_M7.9 GB
Coding
OC
OceanGPT 2B v0.1
Oceangpt · RichardErkhov
Params2.72B
Context4K
Q4_K_M1.8 GB
GGUF
GE
Gemma 2b
Gemma · RichardErkhov
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
GE
bitshrine gemma 2 2B it hermes function calling
Gemma · RichardErkhov
Params2.61B
Context8K
Q4_K_M1.7 GB
Tool use
GP
ST23423 gpt2 pretrained custom eli5tech
Gpt · RichardErkhov
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
QW
Qwen2 Math 7b Sft OpenHermes2.5_continue_with_WebInstructSub Checkpoint 1000
Qwen · RichardErkhov
Params7.62B
Context4K
Q4_K_M4.7 GB
Tool use
UN
Unbabel TowerBase 7B v0.1
Unbabel · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
MI
cognitivecomputations dolphin 2.1 mistral 7b
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
mlfoundations dev llama3 1 8b oh dcft v1 wo evol instruct
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
CodeLlama-7B-fp16
Llama · RichardErkhov
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
TR
Trendyol LLM 7b Chat v1.8
Trendyol · RichardErkhov
Params7.34B
Context32K
Q4_K_M4.4 GB
GGUF
XU
XuanYuan 13B Chat
Xuanyuan · RichardErkhov
Params13.1B
Context8K
Q4_K_M7.9 GB
GGUF
MI
clowman openchat mistral 7b reproduce
Mistral · RichardErkhov
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
MI
pszemraj Mistral v0.3 6B
Mistral · RichardErkhov
Params5.94B
Context32K
Q4_K_M3.6 GB
GGUF
TI
TinyLlama-1.1B-Chat-v1.0-solidworks-intro
Tinyllama · RichardErkhov
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
YI
Faro Yi 34B DPO
Yi · RichardErkhov
Params34.4B
Context32K
Q4_K_M20.7 GB
GGUF
LL
Llama-3.2-3B-Instruct-cot-19-11-5
Llama · RichardErkhov
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
AL
allknowingroger MultiMash 12B slerp
Allknowingroger · RichardErkhov
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
ME
mergekit community final test 4 v2 original old recipe humanish base
Mergekit · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
mlfoundations dev llama3 1 8b oh v3.1 wo glaive code assistant
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
Coding
LL
llama-traditional-chinese-120M
Llama · RichardErkhov
Params120M
Context2K
Q4_K_M0.1 GB
GGUF
LL
BEGADE llama 3.2 3b it ChatBot
Llama · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
RI
101M 0.4
Richarderkhov · RichardErkhov
Params137M
Context1K
Q4_K_M0.1 GB
GGUF
MI
vicgalle Configurable Mistral 7B
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
cais HarmBench Mistral 7b val cls
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

Keep browsing