Q4_K GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 16028 models have a Q4_K file. Sizes run from 1M to 5632B parameters. The longest trained context is 102400K tokens.
SM
SmolLM 135M
SmolLM · RichardErkhov
Params135M
Context2K
Q4_K_M0.1 GB
ST
Starcoderbase 1b
StarCoder · RichardErkhov
Params1.14B
Context8K
Q4_K_M0.8 GB
QW
Qwen3 VL 8B Thinking
Qwen · NexaAI
Params8.19B
Context—
Smallest4.6 GB
MI
laser-dolphin-mixtral-4x7b-dpo
Mistral · RichardErkhov
Params24.2B
Context32K
Q4_K_M14.6 GB
GE
gemma-1.1-7b-it
Gemma · RichardErkhov
Params8.54B
Context8K
Q4_K_M5.3 GB
DO
DolphinStar-12.5B
Dolphinstar · RichardErkhov
Params12.5B
Context32K
Q4_K_M7.5 GB
HE
Heejindo rationale model e10 save5000
Heejindo · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
CH
chinese alpaca 2 13b
Chinese · hfl
Params13.3B
Context4K
Smallest5.0 GB
PR
prometheus-7b-v2.0
Prometheus · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
EN
Envoid Yousei 22B
Envoid · RichardErkhov
Params21.8B
Context4K
Q4_K_M13.2 GB
QW
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen · Svenuks
Params34.7B
Context256K
Q4_K_M21.2 GB
LL
aifeifei798 llama3 8B DarkIdol 2.3 Uncensored 32K
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
ML
mlfoundations dev OH DCFT V3 wo unreplicated
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
TE
tenyx TenyxChat 8x7B v1
Tenyx · RichardErkhov
Params56B
Context32K
Q4_K_M28.4 GB
IN
interview eval zephyr 7b stem test
Interview · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
mlfoundations dev llama2 oh teknium scaling down random 0.3
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
TI
TIPO 100M
Tipo · RichardErkhov
Params100M
Context8K
Q4_K_M0.1 GB
LL
ADT7 SN11 hermes llama3 v6
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
Fsfrm_Llama2_Sft_Ver2_Iter1_Dpo
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
CodeLlama 13b Python Hf
Llama · RichardErkhov
Params13B
Context16K
Q4_K_M7.9 GB
ST
SD3.5 Large GGUF mixed sdcpp
Stable · stduhpf
Params8.23B
Context—
Smallest4.7 GB
WA
wamegabe tinyllama wame 4bit curi
Wamegabe · RichardErkhov
Params1.1B
Context2K
Q4_K_M0.7 GB
LL
Llama-3-8b-64k-PoSE
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
DA
Darkknight535 OpenCrystal 12B L3
Darkknight · RichardErkhov
Params11.5B
Context8K
Q4_K_M7.0 GB
LU
XL LuaCopilot 1.7B FFT
Luacopilot · nwdxlgzs
Params1.72B
Context40K
Q4_K_M1.1 GB
LL
CodeLlama 7b Instruct Hf
Llama · RichardErkhov
Params6.74B
Context16K
Q4_K_M4.1 GB
ML
mlfoundations dev oh teknium scaling down random 0.5
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
antonytm codellama 34b bnb 4bit sitecore so
Llama · RichardErkhov
Params6.74B
Context16K
Q4_K_M4.1 GB
MO
moonshine-tiny
Moonshine · cstr
Params27M
Context—
Smallest0.0 GB
WH
whisper vad encdec asmr
Whisper · cstr
Params30M
Context—
Smallest0.0 GB