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
WA
Wan2.2 I2V A14B
Wan · bullerwins
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
TR
Translategemma 4b It
Translategemma · bullerwins
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
WA
Wan2.2 T2V A14B
Wan · bullerwins
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
TR
Translategemma 12b It
Translategemma · bullerwins
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
FL
FLUX.1 Kontext dev
Flux · bullerwins
Params11.9B
Context—
Q4_K_M6.9 GB
GGUF
TR
Translategemma 27b It
Translategemma · bullerwins
Params27B
Context128K
Q4_K_M16.5 GB
Vision
GE
Huihui Gemma 4 26B A4B It Abliterated
Gemma · bullerwins
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
DE
DeepSeek V3 Bf16
DeepSeek · bullerwins
Params671B
Context160K
Q4_K_M404.4 GB
Tool use
LL
Meta Llama 3.1 405B Instruct
Llama · bullerwins
Params410B
Context128K
Q4_K_M245.7 GB
GGUF
LL
Meta Llama 3.1 70B Instruct
Llama · bullerwins
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
DE
DeepSeek-Coder-V2-Instruct
DeepSeek · bullerwins
Params236B
Context160K
Smallest133.9 GB
Coding
QW
Qwen3 4B Instruct 2507
Qwen · bullerwins
Params4.02B
Context256K
Q4_K_M2.5 GB
Tool use
DE
DeepSeek V4 Flash
DeepSeek · bullerwins
Params284B
Context1024K
Smallest88.0 GB
GGUF
LL
Meta Llama 3.1 8B Instruct
Llama · bullerwins
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
DE
DeepSeek V2 Chat 0628
DeepSeek · bullerwins
Params236B
Context160K
Q4_K_M142.5 GB
GGUF
DE
DeepSeek V4 Flash 0731
DeepSeek · bullerwins
Params284B
Context—
Smallest0.5 GB
GGUF
DE
keys DeepSeekV4 Flash GA 0731 Dspark Abliterated 32 32
DeepSeek · bullerwins
Params19.8B
Context1024K
Smallest10.9 GB
GGUF
QW
Qwen3 VL 32B Instruct
Qwen · bullerwins
Params32.8B
Context256K
Q4_K_M19.8 GB
Tool useVision
LL
Reflection Llama 3.1 70B
Llama · bullerwins
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
QW
Qwen2.5 7B Instruct
Qwen · bullerwins
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
HU
Hunyuan A13B Instruct Hf
Hunyuan · bullerwins
Params80.4B
Context256K
Q4_K_M48.8 GB
ReasoningTool use
QW
Qwen3 Coder 30B A3B Instruct
Qwen · bullerwins
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
QW
Qwen3 8B
Qwen · bullerwins
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen3 30B A3B Instruct 2507
Qwen · bullerwins
Params30.5B
Context256K
Q4_K_M18.6 GB
Tool use
QW
Qwen3 14B
Qwen · bullerwins
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
KI
Kimi Dev 72B
Kimi · bullerwins
Params72.7B
Context128K
Q4_K_M47.4 GB
CodingTool use
DE
DeepSeek V2.5
DeepSeek · bullerwins
Params236B
Context160K
Q4_K_M142.5 GB
Tool use
MI
MiniMax M2
Minimax · bullerwins
Params229B
Context192K
Q4_K_M138.3 GB
ReasoningTool use
AT
Athene 70B
Athene · bullerwins
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
MI
MiniMax M2.1 REAP 50
Minimax · bullerwins
Params116B
Context192K
Q4_K_M70.4 GB
CodingReasoningTool use

About bullerwins on Hugging Face

bullerwins has published 43 GGUF models that ggufmodels.com tracks, across families such as DeepSeek, Qwen and Llama. The most downloaded are Wan2.2 I2V A14B, Translategemma 4b It and Wan2.2 T2V A14B.

The quants bullerwins publishes most often are Q4_K_M (35), Q8_0 (34), Q6_K (34) and Q5_K_M (34). Their Q4_K_M files range from 2.5 to 404.5 GB. Parameter counts run from 596M to 2780B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has bullerwins published?

43 models are listed here, mainly from the DeepSeek, Qwen and Llama families. The most downloaded is Wan2.2 I2V A14B.

Which quants does bullerwins publish?

The most common are Q4_K_M (35 models), Q8_0 (34 models), Q6_K (34 models) and Q5_K_M (34 models).

Keep browsing