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.
LL
Llama3 KALE LM Chem 1.5 8B
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GE
Gemma 2b
Gemma · RichardErkhov
Params2.51B
Context8K
Q4_K_M1.6 GB
LL
meta llama CodeLlama 34b Instruct hf
Llama · RichardErkhov
Params33.7B
Context16K
Q4_K_M20.2 GB
LL
Meta Llama 3.1 8B Instruct
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
llama 2 7b langchain chat
Llama · shaowenchen
Params6.74B
Context4K
Smallest2.8 GB
HO
K2 Horizon 7B
Horizon · eaddario
Params9B
Context512K
Smallest0.0 GB
QW
Ebai3.6 27b unscensored
Qwen · vathvathv
Params26.9B
Context256K
Smallest10.0 GB
MI
K2S3 Mistral 7b v1.0
Mistral · RichardErkhov
Params7.37B
Context32K
Q4_K_M4.5 GB
IN
InternLM2
InternLM · legraphista
Params7.74B
Context256K
Smallest1.9 GB
BA
baichuan2 7b base
Baichuan · shaowenchen
Params7.51B
Context4K
Smallest3.3 GB
MI
Ministral 3 14B Reasoning 2512
Mistral · eaddario
Params13.5B
Context256K
Q4_K_M8.2 GB
PR
Prometheus 8x7b v2.0
Prometheus · RichardErkhov
Params46.7B
Context32K
Q4_K_M28.4 GB
QW
Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive
Qwen · zihuiliu7737
Params122B
Context256K
Q4_K_M74.2 GB
QW
Qwen3.8-27B
Qwen · bramburn
Params27.3B
Context256K
Q4_K_M16.6 GB
QW
Qwen3.6 Uncensored Aggressive
Qwen · tripolskypetr
Params26.9B
Context256K
Q4_K_M21.2 GB
NO
nothingiisreal MN 12B Starcannon v2
Nothingiisreal · RichardErkhov
Params12.2B
Context1000K
Q4_K_M7.5 GB
OL
Olmo 3 7B Instruct
OLMo · eaddario
Params7.3B
Context64K
Q4_K_M4.5 GB
GE
Gemma 4 Uncensored Aggressive
Gemma · tripolskypetr
Params4.65B
Context128K
Q4_K_M5.3 GB
PH
Borea Phi 3.5 Mini Instruct Common
Phi · RichardErkhov
Params3.82B
Context128K
Q4_K_M2.4 GB
LL
Llama2 12.8b_lora Dpo_V1
Llama · RichardErkhov
Params13B
Context4K
Q4_K_M7.9 GB
SC
scottsuk0306 zephyr 7b math test
Scottsuk · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GE
gemma-7b-it
Gemma · RichardErkhov
Params8.54B
Context8K
Q4_K_M5.3 GB
LL
ArliAI Llama 3 8B Formax v1.0
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
LI
lightblue reranker 0.5 cont filt
Lightblue · RichardErkhov
Params630M
Context32K
Q4_K_M0.5 GB
UN
Unbabel TowerInstruct 7B v0.1
Unbabel · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
LL
Llama3 Med42 8B
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Qwen3.5 2B
Qwen · titan0115
Params1.88B
Context256K
Q4_K_M1.3 GB
LL
chinese llama 2 7b 64k
Llama · hfl
Params6.93B
Context64K
Smallest2.6 GB
LL
YBXL Med LLaMA3 8B
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GE
Gemma 2 9b It
Gemma · RichardErkhov
Params9.24B
Context8K
Q4_K_M5.8 GB