Q3_K GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 15171 models have a Q3_K file. Sizes run from 1M to 5632B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
SA
SambaLingo Turkish Chat
Sambalingo · RichardErkhov
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
BR
BroAlanTaps GPT2 large 4 34000steps
Broalantaps · RichardErkhov
Params839M
Context1K
Q4_K_M0.5 GB
GGUF
ME
mergekit community mergekit slerp tsuvyfz
Mergekit · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
pucpr br Clinical BR Mistral 7B v0.2
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
jesse tong llama 2 7b chat newspaper vi
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
LL
nvidia OpenMath2 Llama3.1 70B
Llama · RichardErkhov
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
QW
Ostrich 32B Qwen3 260303
Qwen · etemiz
Params32.8B
Context40K
Smallest9.0 GB
ReasoningTool use
QW
Qwen2.5 0.5B
Qwen · RichardErkhov
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
QW
Qwen2.5 Math 1.5B
Qwen · RichardErkhov
Params1.54B
Context4K
Q4_K_M1.0 GB
Tool use
BL
Bloom 7b1
Bloom · RichardErkhov
Params8.1B
Context4K
Q4_K_M5.3 GB
GGUF
LL
mlfoundations dev llama2 oh teknium scaling down random 1.0
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
LL
broalantap Llama3 Compressor Adapter 4 20000steps
Llama · RichardErkhov
Params839M
Context1K
Q4_K_M0.5 GB
GGUF
CH
ChemDFM 13B v1.0
Chemdfm · RichardErkhov
Params13.1B
Context2K
Q4_K_M7.9 GB
GGUF
BR
BroAlanTaps GPT2 large 64 15750steps
Broalantaps · RichardErkhov
Params838M
Context1K
Q4_K_M0.5 GB
GGUF
QW
Qwen2.5 1.5B Instruct
Qwen · RichardErkhov
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
VI
vilm vinallama 12.5b chat DUS
Vilm · RichardErkhov
Params12.5B
Context4K
Q4_K_M7.6 GB
GGUF
MI
mistral-11b-slimorca
Mistral · RichardErkhov
Params10.7B
Context32K
Q4_K_M6.5 GB
GGUF
LL
Llama 3.2 1B Instruct Ja
Llama · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LL
realshyfox sharded Llama 3 8B
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
Kabster Bio Mistralv2 Squared
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr-7b-dpo-full-prompt-extend-chosen
Zephyr · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
irlab udc Llama 3.1 8B Instruct Galician
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
DE
deepnet C00ReadyModel
Deepnet · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
GE
gemma-2b-ForexAI
Gemma · RichardErkhov
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
LL
Hermes 2 Theta Llama 3 70B
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
Tool use
LL
Dolphin 3.0 Llama 3.1 8B
Llama · R4xx1
Params8.03B
Context128K
Q4_K_M4.9 GB
CodingTool use
QW
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP
Qwen · jchonde
Params1.86B
Context256K
Smallest0.9 GB
GGUF
LL
Llama 3.2 1B
Llama · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
OA
h2oai h2o danube2 1.8b sft
Oai · RichardErkhov
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
IA
iamspathan half girlfriend gpt2
Iamspathan · RichardErkhov
Params163M
Context1K
Q4_K_M0.1 GB
GGUF

Other quants

Keep browsing