GGUF models by hus960
47 GGUF models quantized by hus960 on Hugging Face. Sizes run from 2.78B to 58.3B parameters. The longest trained context is 1024K tokens.
QW
firefly-qwen1.5-en-7b-dpo-v0.1
Qwen · hus960
Params7.72B
Context32K
Q4_K_M4.8 GB
OL
OLMo 2 1124 13B Instruct
OLMo · hus960
Params13.7B
Context4K
Q4_K_M8.4 GB
EX
Experiment30 7B Q4 K M
Experiment · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
JA
jaskier 7b dpo v6.1 Q4 K M
Jaskier · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
Infinity Instruct 7M Gen Llama3_1 8B
Llama · hus960
Params8.03B
Context8K
Q4_K_M4.9 GB
DO
DownSide-2x7B-Toxic-TOM-RP-TruthyDPO
Downside · hus960
Params12.9B
Context32K
Q4_K_M7.8 GB
QW
openbuddy-qwen1.5-32b-v21.2-32k
Qwen · hus960
Params32.5B
Context32K
Q4_K_M19.7 GB
MI
Einstein v6 7B Q4 K M
Mistral · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
OR
OrpoLlama-3-8B
Orpollama · hus960
Params8.03B
Context8K
Q4_K_M4.9 GB
MI
Tess-2.0-Mixtral-8x7B-v0.2
Mistral · hus960
Params46.7B
Context32K
Q4_K_M28.4 GB
MI
MistralTrix8x9B
Mistral · hus960
Params58.3B
Context32K
Smallest21.6 GB
MI
base 7b v0.2 Q4 K M
Mistral · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
KU
Nyan Stunna 7B Q4 K M
Kukulstanta · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
MA
Matter-0.2-32B
Matter · hus960
Params32.5B
Context32K
Q4_K_M19.7 GB
IC
IceCoffeeRP 7b Q4 K M
Icecoffeerp · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
NO
WestIceLemonTeaRP 32k 7b Q4 K M
Not · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
PR
Lelanta lake 7b Q4 K M
Prima · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB