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.

Most downloadedNewestLargestLongest contextSmallest
LL
L3-Aethora-15B-V2
Llama · bullerwins
Params15B
Context8K
Q4_K_M9.1 GB
GGUF
CE
L3.1 8B Celeste V1.5
Celeste · bullerwins
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
SA
Sao10K_L3-70B-Euryale-v2.1_86c36496757f75d519450af41726813ce026028e
Sao · bullerwins
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
DE
DeepSeek V3.1 BF16
DeepSeek · bullerwins
Params671B
Context160K
Q4_K_M404.5 GB
ReasoningTool use
GE
Gemma 2 2b It
Gemma · bullerwins
Params2.61B
Context8K
Smallest2.2 GB
GGUF
DE
DeepSeek R1 0528
DeepSeek · bullerwins
Params671B
Context160K
Q4_K_M404.5 GB
ReasoningTool use
MI
MiniMax M2.1
Minimax · bullerwins
Params229B
Context192K
Smallest162.3 GB
ReasoningTool use
DE
DeepSeek R1 0528 Qwen3 8B
DeepSeek · bullerwins
Params8.19B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
DE
DeepSeek R1T Chimera Bf16
DeepSeek · bullerwins
Params671B
Context160K
Q4_K_M404.5 GB
ReasoningTool use
QW
Qwen3 Embedding 0.6B
Qwen · bullerwins
Params596M
Context32K
Smallest0.6 GB
EmbeddingReasoningTool use
KI
Kimi K3
Kimi · bullerwins
Params2780B
Context1024K
Smallest1561.2 GB
GGUF
MA
mathstral-7B-v0.1
Mathstral · bullerwins
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
DE
DeepSeek TNG R1T2 Chimera BF16
DeepSeek · bullerwins
Params671B
Context160K
Q4_K_M404.5 GB
Tool use

Keep browsing