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.
PH
Phi 3.5 Mini IFRS Accountant
Phi · RichardErkhov
Params3.82B
Context128K
Q4_K_M2.3 GB
AK
akshit Gupta smol360M fullnew merged FinetunedByAG
Akshit · RichardErkhov
Params362M
Context2K
Q4_K_M0.3 GB
FP
FPHam L3 8B Everything COT
Fpham · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
SU
supermario v2
Supermario · andrijdavid
Params7.24B
Context32K
Q4_K_M4.4 GB
GP
sp8108 gpt2 finetuned ros2 v3
Gpt · RichardErkhov
Params163M
Context1K
Q4_K_M0.1 GB
QW
trl internal testing tiny Qwen2ForCausalLM 2.5 Coder
Qwen · RichardErkhov
Params11M
Context—
Q4_K_M0.0 GB
WE
Wenzhong-GPT2-110M
Wenzhong · RichardErkhov
Params163M
Context1K
Q4_K_M0.1 GB
ML
mlfoundations dev oh dcft v1.1 no curation
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
OP
OpenELM 1_1B IPO
Openelm · RichardErkhov
Params1.08B
Context2K
Q4_K_M0.7 GB
LL
Meta LLama 3 Cat A LLama 70b
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
BL
Bloom 7b1
Bloom · RichardErkhov
Params8.1B
Context4K
Q4_K_M5.3 GB
MI
cognitivecomputations dolphin 2.6 mistral 7b
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
Suzume Llama 3 8B Multilingual
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
KA
Katayoon DPO ONLY Zephyr 7B 3 iter 2
Katayoon · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
VO
vonPipe selfiesPretrainInstruct
Vonpipe · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
SO
SOLAR 10.7B Instruct STOCK_SOLAR Slerp
Solar · RichardErkhov
Params10.7B
Context4K
Q4_K_M6.5 GB
LL
zomd AISquare Instruct llama2 koen 13b v0.9.19
Llama · RichardErkhov
Params13.2B
Context2K
Q4_K_M8.0 GB
MI
mlfoundations dev hp ablations mistral scheduler cosine warmup0.10 dcftv1.2
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
Vbd Llama2 7B 50b Chat
Llama · RichardErkhov
Params6.88B
Context4K
Q4_K_M4.2 GB
MI
mlfoundations dev hp ablations mistral epoch2 dcftv1.2
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
mlfoundations dev hp ablations mistral bsz1024
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
DA
Dans Archive Dans MysteryModel 13b
Dans · RichardErkhov
Params13B
Context4K
Q4_K_M7.9 GB
QW
Qwen2.5 3B Instruct
Qwen · RichardErkhov
Params3.09B
Context32K
Q4_K_M1.9 GB
LL
jamesohe Llama3 CAS Audit8B GCNI V3
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
MI
Mistral Mcqa Circuit Broken
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
ML
mlfoundations dev oh v1.3 camel chemistry x4
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GE
Gemma 2b It SFT D1_chosen Orca
Gemma · RichardErkhov
Params2.51B
Context8K
Q4_K_M1.6 GB
LL
Llama 3.2 1B Instruct De
Llama · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
NI
NIyengar doct qna finetune gpt2
Niyengar · RichardErkhov
Params163M
Context1K
Q4_K_M0.1 GB
RE
reflect_llm8B_Om2SftT2_Om2G8kOm2AgBlcIpsdpIter1T02_b0.1
Reflect · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB