GGUF models by Bluerosesbutterfly

38 GGUF models quantized by Bluerosesbutterfly on Hugging Face. Sizes run from 1B to 1030B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen2.5 3B Instruct Abliterated
Qwen · Bluerosesbutterfly
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
LL
Llama 3.3 70B Abliterated
Llama · Bluerosesbutterfly
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
Llama 4 Scout 17B 16E Instruct Abliterated v2
Llama · Bluerosesbutterfly
Params110B
Context10240K
Q4_K_M65.4 GB
GGUF
GE
Gemma 2 9b It
Gemma · Bluerosesbutterfly
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
QW
Huihui Qwen3 30B A3B Instruct 2507 Abliterated
Qwen · Bluerosesbutterfly
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningTool use
LL
Huihui Mistral Small 3.2 24B Instruct 2506 Abliterated Llamacppfixed
Llama · Bluerosesbutterfly
Params23.6B
Context128K
Q4_K_M14.3 GB
Tool use
KI
Kimi Dev 72B Abliterated
Kimi · Bluerosesbutterfly
Params72.7B
Context128K
Q4_K_M47.4 GB
Tool use
DE
DeepSeek R1 Distill Qwen 14B abliterated v2.Q4 K M
DeepSeek · Bluerosesbutterfly
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
MI
Mistral Nemo 2407 12B Thinking Claude Gemini GPT5.2 Uncensored HERETIC
Mistral · Bluerosesbutterfly
Params12.2B
Context1000K
Q4_K_M7.5 GB
Reasoning
MI
Midnight Miqu 70b v1.5
Midnight · Bluerosesbutterfly
Params69B
Context32K
Q4_K_M41.4 GB
GGUF
LL
Meta Llama 3.1 8B Instruct abliterated.Q4 K M
Llama · Bluerosesbutterfly
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
GE
Gemma 3 4b It Abliterated v2
Gemma · Bluerosesbutterfly
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
GE
Gemma 3 1b It Abliterated v2
Gemma · Bluerosesbutterfly
Params1B
Context32K
Smallest1.1 GB
GGUF
LL
Llama 3.3_8B_Abliterated
Llama · Bluerosesbutterfly
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
GE
Gemma 2 9b It
Gemma · Bluerosesbutterfly
Params9.24B
Context8K
Smallest6.6 GB
GGUF
DE
DeepSeek R1 Distill Qwen 14B Abliterated v2
DeepSeek · Bluerosesbutterfly
Params14.8B
Context128K
Smallest12.1 GB
ReasoningTool use
QW
Huihui Qwen3.5 27B Abliterated
Qwen · Bluerosesbutterfly
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
QW
Qwen2.5 7B Instruct abliterated v2.Q4 K M
Qwen · Bluerosesbutterfly
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
DE
DeepSeek R1 Distill Llama 8B Abliterated
DeepSeek · Bluerosesbutterfly
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
KI
Huihui Kimi K2.5 BF16 Abliterated
Kimi · Bluerosesbutterfly
Params1030B
Context256K
Smallest489.1 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 14B Abliterated v2
DeepSeek · Bluerosesbutterfly
Params14.8B
Context128K
Smallest15.7 GB
ReasoningTool use
HE
Hermes-4-70B
Hermes · Bluerosesbutterfly
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
QW
Qwen3.6 27B Claude Opus Sonnet DistilledV2 MTP
Qwen · Bluerosesbutterfly
Params27.3B
Context256K
Smallest22.4 GB
ReasoningTool use
CO
C4Ai Command R Plus 08 2024
Command R · Bluerosesbutterfly
Params104B
Context128K
Q4_K_M62.8 GB
GGUF
MI
Mistral Small 24B Instruct 2501 Abliterated
Mistral · Bluerosesbutterfly
Params23.6B
Context32K
Smallest11.5 GB
GGUF
DE
DeepSeek R1 Distill Qwen 32B Abliterated
DeepSeek · Bluerosesbutterfly
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
MI
Mistral Large 3 675B Instruct 2512
Mistral · Bluerosesbutterfly
Params673B
Context288K
Smallest216.2 GB
Tool use
MI
Mistral Helcyon Mercury 12b v3.0 Q4 K M
Mistral · Bluerosesbutterfly
Params12.2B
Context128K
Q4_K_M7.5 GB
Tool use
QW
Huihui Qwen3 VL 32B Thinking Abliterated
Qwen · Bluerosesbutterfly
Params32.8B
Context256K
Q4_K_M19.8 GB
ReasoningTool useVision
KI
Kimi K25 Abliterated
Kimi · Bluerosesbutterfly
Params1030B
Context256K
Smallest372.9 GB
ReasoningTool use

About Bluerosesbutterfly on Hugging Face

Bluerosesbutterfly has published 38 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Gemma. The most downloaded are Qwen2.5 3B Instruct Abliterated, Llama 3.3 70B Abliterated and Llama 4 Scout 17B 16E Instruct Abliterated v2.

The quants Bluerosesbutterfly publishes most often are Q4_K_M (25), Q8_0 (3), Q6_K (3) and Q5_K_M (1). Their Q4_K_M files range from 1.9 to 455.9 GB. Parameter counts run from 1B to 1030B, and the longest trained context window is 10240K tokens.

Frequently asked questions

What GGUF models has Bluerosesbutterfly published?

38 models are listed here, mainly from the Qwen, Llama and Gemma families. The most downloaded is Qwen2.5 3B Instruct Abliterated.

Which quants does Bluerosesbutterfly publish?

The most common are Q4_K_M (25 models), Q8_0 (3 models), Q6_K (3 models) and Q5_K_M (1 models).

Keep browsing