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.

Most downloadedNewestLargestLongest contextSmallest
MI
dolphin 2.8 mistral 7b v02 Q4 K M
Mistral · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingTool use
LL
Llama-3-13B-Instruct
Llama · hus960
Params13.3B
Context8K
Q4_K_M8.1 GB
GGUF
LL
Einstein-v6.1-Llama3-8B
Llama · hus960
Params8.03B
Context8K
Q4_K_M4.9 GB
Tool use
QW
openbuddy-qwen1.5-14b-v21.1-32k
Qwen · hus960
Params14.2B
Context32K
Q4_K_M9.2 GB
GGUF
LL
LLama3-Gaja-Hindi-8B-v0.1
Llama · hus960
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-8b.UNLEASHED
Llama · hus960
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
FrankenLlama-3-12B-Instruct
Llama · hus960
Params11.5B
Context8K
Q4_K_M7.0 GB
GGUF
ER
Eris LelantaclesV2 7b Q4 K M
Eris · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
llama-3-8b-256k-PoSE
Llama · hus960
Params8.03B
Context512K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-SLERP-8B
Llama · hus960
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Scarlett-Llama-3-8B-v1.0
Llama · hus960
Params8.03B
Context8K
Q4_K_M4.9 GB
Coding
WA
wavecoder-pro-6.7b
Wavecoder · hus960
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
LA
Laylewcules 7B v.02 Q4 K M
Laylewcules · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
llama-3-8b-1m-PoSE
Llama · hus960
Params8.03B
Context1024K
Q4_K_M4.9 GB
GGUF
MA
Matter 0.2 7B DPO Q4 K M
Matter · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OL
OLMo 2 1124 7B Instruct Q4 K M
OLMo · hus960
Params7.3B
Context4K
Q4_K_M4.5 GB
GGUF
NX
Nxcode-CQ-7B-orpo
Nxcode · hus960
Params7.25B
Context64K
Q4_K_M4.7 GB
Coding
MI
Mini-Mixtral-v0.2
Mistral · hus960
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
LL
Unsafe-Llama-3-8B
Llama · hus960
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MU
multimaster-7b-v6
Multimaster · hus960
Params35.4B
Context32K
Q4_K_M21.4 GB
GGUF
PH
Einstein v4 phi2 Q8 0
Phi · hus960
Params2.78B
Context2K
Smallest3.0 GB
CodingTool use
OL
OLMo 2 1124 13B Instruct RLVR2
OLMo · hus960
Params13.7B
Context4K
Q4_K_M8.4 GB
GGUF
RA
Raiden-16x3.43B
Raiden · hus960
Params35.8B
Context2K
Q4_K_M26.8 GB
GGUF
KU
Stanta Lelemon Maid 7B Q4 K M
Kukulstanta · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama-3-NeuralPaca-8b
Llama · hus960
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
PS
PsychoOrca_32x1.1B_MoE_bf16
Psychoorca · hus960
Params24.7B
Context2K
Smallest14.9 GB
Coding
PR
Prima LelantaclesV7 experimentalv2 7b Q4 K M
Prima · hus960
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
LLaMA 3.1 8B Infinity3M Kobo Q4 K M
Llama · hus960
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Unholy-Aura-Llama-3-8B
Llama · hus960
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
openbuddy mistral2 7b v20.3 32k Q4 K M
Mistral · hus960
Params7.28B
Context32K
Q4_K_M4.4 GB
GGUF

About hus960 on Hugging Face

hus960 has published 47 GGUF models that ggufmodels.com tracks, across families such as Llama, Mistral and Qwen. The most downloaded are dolphin 2.8 mistral 7b v02 Q4 K M, Llama-3-13B-Instruct and Einstein-v6.1-Llama3-8B.

The quants hus960 publishes most often are Q4_K_M (44), Q8_0 (1), Q2_K (1) and BF16 (1). Their Q4_K_M files range from 4.1 to 28.4 GB. Parameter counts run from 2.78B to 58.3B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has hus960 published?

47 models are listed here, mainly from the Llama, Mistral and Qwen families. The most downloaded is dolphin 2.8 mistral 7b v02 Q4 K M.

Which quants does hus960 publish?

The most common are Q4_K_M (44 models), Q8_0 (1 models), Q2_K (1 models) and BF16 (1 models).

Keep browsing