GGUF models by bullerwins
43 GGUF models quantized by bullerwins on Hugging Face. Sizes run from 596M to 2780B parameters. The longest trained context is 1024K tokens.
LL
L3-Aethora-15B-V2
Llama · bullerwins
Params15B
Context8K
Q4_K_M9.1 GB
CE
L3.1 8B Celeste V1.5
Celeste · bullerwins
Params8.03B
Context128K
Q4_K_M4.9 GB
SA
Sao10K_L3-70B-Euryale-v2.1_86c36496757f75d519450af41726813ce026028e
Sao · bullerwins
Params70.6B
Context8K
Q4_K_M42.5 GB
DE
DeepSeek V3.1 BF16
DeepSeek · bullerwins
Params671B
Context160K
Q4_K_M404.5 GB
GE
Gemma 2 2b It
Gemma · bullerwins
Params2.61B
Context8K
Smallest2.2 GB
DE
DeepSeek R1 0528
DeepSeek · bullerwins
Params671B
Context160K
Q4_K_M404.5 GB
MI
MiniMax M2.1
Minimax · bullerwins
Params229B
Context192K
Smallest162.3 GB
DE
DeepSeek R1 0528 Qwen3 8B
DeepSeek · bullerwins
Params8.19B
Context128K
Q4_K_M5.0 GB
DE
DeepSeek R1T Chimera Bf16
DeepSeek · bullerwins
Params671B
Context160K
Q4_K_M404.5 GB
QW
Qwen3 Embedding 0.6B
Qwen · bullerwins
Params596M
Context32K
Smallest0.6 GB
KI
Kimi K3
Kimi · bullerwins
Params2780B
Context1024K
Smallest1561.2 GB
MA
mathstral-7B-v0.1
Mathstral · bullerwins
Params7.25B
Context32K
Q4_K_M4.4 GB
DE
DeepSeek TNG R1T2 Chimera BF16
DeepSeek · bullerwins
Params671B
Context160K
Q4_K_M404.5 GB