phi0112358/DeepSeek-V2-Lite-Chat-Q4_0-GGUF
16B
•
Updated
•
11
LLM: MoEs
GGUFs, conventional and k-quants – both without imatrix. This should be faster for CPU inference. Right now DeepSee MoEs (Mixture of Experts)
-
-
phi0112358/DeepSeek-V2-Lite-Chat-Q8_0-GGUF
16B • Updated • 3 -
phi0112358/DeepSeek-Coder-V2-Lite-Base-Q4_K_S-GGUF
16B • Updated • 14 -
phi0112358/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M-GGUF
16B • Updated • 6 -
phi0112358/DeepSeek-Coder-V2-Lite-Instruct-Q8_0-GGUF
16B • Updated • 23 -
XiaomiMiMo/MiMo-V2-Flash
Text Generation • Updated • 353k • • 629 -
unsloth/MiMo-V2-Flash-GGUF
309B • Updated • 3.1k • 13 -
XiaomiMiMo/MiMo-V2-Flash-Base
Text Generation • 310B • Updated • 171 • 42 -
MiniMaxAI/MiniMax-M2
Text Generation • Updated • 508k • • 1.48k -
MiniMaxAI/MiniMax-M2.1
Text Generation • Updated • 75.5k • • 1.26k -
zai-org/GLM-4.7
Text Generation • Updated • 121k • • 1.93k -
zai-org/GLM-4.7-Flash
Text Generation • Updated • 1.75M • • 1.55k -
zai-org/GLM-4.6V
Image-Text-to-Text • Updated • 7.24k • • 376 -
zai-org/GLM-4.5-Air-Base
Text Generation • Updated • 1.27k • 43 -
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Text Generation • Updated • 1.03M • 638 -
nex-agi/DeepSeek-V3.1-Nex-N1
Text Generation • 671B • Updated • 30 • 42 -
arcee-ai/Trinity-Large-Preview
Text Generation • 399B • Updated • 1.89k • 144 -
arcee-ai/Trinity-Large-TrueBase
Text Generation • Updated • 404 • 61 -
arcee-ai/Trinity-Mini-GGUF
Text Generation • 26B • Updated • 2.48k • 52 -
stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S
Text Generation • 197B • Updated • 16.7k • 130 -
nvidia/GR00T-N1.6-DROID
Robotics • 3B • Updated • 150 • 6 -
moonshotai/Kimi-Linear-48B-A3B-Instruct
Text Generation • 49B • Updated • 29.3k • 541 -
moonshotai/Kimi-VL-A3B-Instruct
Image-Text-to-Text • 16B • Updated • 181k • 255 -
SamsungSAILMontreal/Qwen3-Next-80B-A3B-Instruct-REAM
Text Generation • 60B • Updated • 27 • 3 -
lovedheart/Kimi-Linear-REAP-35B-A3B-Instruct-GGUF
35B • Updated • 212 • 1