GGUF models by NikolayKozloff
1011 GGUF models quantized by NikolayKozloff on Hugging Face. Sizes run from 30M to 33.1B parameters. The longest trained context is 1024K tokens.
PO
poemma 12B Q5 K M
Poemma · NikolayKozloff
Params12.2B
Context1000K
Smallest8.7 GB
LL
Llama 3.1 8B ReasonChatV1 Q8 0
Llama · NikolayKozloff
Params8.03B
Context128K
Smallest8.5 GB
LL
Llama 3.1 8B BeyondReality
Llama · NikolayKozloff
Params8.03B
Context128K
Smallest8.5 GB
LL
malaysian-llama-3-8b-instruct-16k
Llama · NikolayKozloff
Params8.03B
Context32K
Smallest8.5 GB
DI
DiscoLM_German_7b_v1
Discolm · NikolayKozloff
Params7.24B
Context32K
Smallest7.7 GB
SA
SambaLingo Slovenian Chat
Sambalingo · NikolayKozloff
Params6.95B
Context4K
Smallest7.4 GB
QR
Qra 7b
Qra · NikolayKozloff
Params6.74B
Context4K
Smallest7.2 GB
ME
Meltemi 7B v1
Meltemi · NikolayKozloff
Params7.48B
Context32K
Smallest8.0 GB
LL
Llama-3SOME-8B-v2
Llama · NikolayKozloff
Params8.03B
Context10K
Smallest5.6 GB
MI
mistral doryV2 12b Q5 K S
Mistral · NikolayKozloff
Params12.2B
Context1000K
Smallest8.5 GB
ME
MetaStone L1 7B
Metastone · NikolayKozloff
Params7.62B
Context128K
Smallest8.1 GB
HY
HyGPT 10b It
Hygpt · NikolayKozloff
Params9.24B
Context8K
Smallest7.6 GB
LL
Awanllm-Llama-3-8B-Cumulus-v1.0
Llama · NikolayKozloff
Params8.03B
Context8K
Smallest4.7 GB
GE
GeM2-Llamion-14B-Chat
Gem · NikolayKozloff
Params14.5B
Context4K
Q4_K_M8.8 GB
MO
Morfoz-LLM-8b-v1.0
Morfoz · NikolayKozloff
Params8.03B
Context8K
Smallest4.7 GB
LL
ParaLex-Llama-3-8B-SFT
Llama · NikolayKozloff
Params8.03B
Context8K
Smallest8.5 GB
AR
Art Skynet 3B Q8 0
Art · NikolayKozloff
Params3.21B
Context128K
Smallest3.4 GB
UI
UIGEN 7B 16bit Q8 0
Uigen · NikolayKozloff
Params7.62B
Context32K
Smallest8.1 GB
AR
ArmenianGPT 0.5 12B
Armeniangpt · NikolayKozloff
Params11.8B
Context128K
Smallest8.2 GB
LL
SFR-Iterative-DPO-LLaMA-3-8B-R
Llama · NikolayKozloff
Params8.03B
Context8K
Smallest8.5 GB
NI
NightyGurps 14b v1.1 Q5 K S
Nightygurps · NikolayKozloff
Params14.8B
Context32K
Smallest10.3 GB