GGUF models by Cran-May

92 GGUF models quantized by Cran-May on Hugging Face. Sizes run from 66M to 72.7B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
OP
OpenBuddy R10528DistillQwen 72B Preview1
Openbuddy · Cran-May
Params72.7B
Context195K
Smallest54.4 GB
ReasoningTool use
QW
Replete Qwen 2.5 3b CoT RP Q5 K M
Qwen · Cran-May
Params3.4B
Context32K
Smallest2.4 GB
RoleplayTool use
QW
XinYuan Qwen2.5 7B 0917 Q4 K M
Qwen · Cran-May
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
LL
Llama 3.1 8B Reason Blend 888k Q5 K M
Llama · Cran-May
Params8.03B
Context128K
Smallest5.7 GB
Tool use
PH
Phi 3.5 Chinese
Phi · Cran-May
Params3.82B
Context128K
Smallest2.8 GB
GGUF
SL
SLIDE v2 Q4 K S
Slide · Cran-May
Params7.28B
Context32K
Smallest4.2 GB
GGUF
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · Cran-May
Params7.62B
Context128K
Smallest5.4 GB
ReasoningTool use
LL
Chinese-LLaMA-2-13B-hf
Llama · Cran-May
Params13.1B
Context2K
Q4_K_M7.9 GB
GGUF
OP
OpenBuddy R10528DistillQwen 4B v27.2
Openbuddy · Cran-May
Params4.02B
Context40K
Smallest2.9 GB
ReasoningTool use
GE
Gemma-2-9B-Chinese-Chat
Gemma · Cran-May
Params9.24B
Context8K
Smallest5.2 GB
GGUF
MI
Infinity Instruct 7M Gen Mistral 7B
Mistral · Cran-May
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
YI
Yi 1.5 9B
Yi · Cran-May
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
PH
Phi 3.5 Mini Instruct
Phi · Cran-May
Params3.82B
Context128K
Smallest2.8 GB
Coding
AN
AnFeng
Anfeng · Cran-May
Params7.72B
Context8K
Smallest4.8 GB
GGUF
QW
FwF Qwen 7B 0.2 Q5 K M
Qwen · Cran-May
Params7.62B
Context32K
Smallest5.4 GB
Tool use
E8
E 8 Q4 K M
Cran-May
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
OP
Openbuddy Wayfarer 70b v25.1 131k
Openbuddy · Cran-May
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
HO
Hormoz
Hormoz · Cran-May
Params8.03B
Context8K
Smallest4.8 GB
GGUF
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · Cran-May
Params8.03B
Context128K
Smallest5.7 GB
ReasoningTool use
OP
openbuddy-yi1.5-9b-v21.1-32k
Openbuddy · Cran-May
Params8.85B
Context32K
Smallest5.1 GB
GGUF
SM
SmolLM2 360M Grpo r999 Q5 K M
SmolLM · Cran-May
Params362M
Context8K
Smallest0.3 GB
GGUF
AP
Apollo2 9B
Apollo · Cran-May
Params9.24B
Context8K
Smallest6.6 GB
GGUF
LL
openbuddy llama3.1 8b v22.3 131k IQ4 XS
Llama · Cran-May
Params8.03B
Context128K
Smallest4.4 GB
GGUF
CE
CEPrune GRPO 12B ignore please duplicate IQ4 XS
Ceprune · Cran-May
Params10.1B
Context1000K
Smallest5.6 GB
GGUF
QW
NQLSG Qwen2.5 14B MegaFusion v5 Roleplay Duplicate
Qwen · Cran-May
Params14.8B
Context32K
Smallest6.7 GB
RoleplayTool use
VI
Viper Coder HybridMini v1.3
Viper · Cran-May
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · Cran-May
Params1.78B
Context128K
Smallest1.1 GB
ReasoningTool use
MI
openbuddy-mistral-22b-v21.1-32k
Mistral · Cran-May
Params22.4B
Context64K
Q4_K_M13.4 GB
GGUF
QW
QwQ 0.5B Distilled SFT
Qwen · Cran-May
Params494M
Context32K
Smallest0.4 GB
ReasoningTool use
LL
openbuddy llama3.1 8b v22.3 131k Q4 K S
Llama · Cran-May
Params8.03B
Context128K
Smallest4.7 GB
GGUF

About Cran-May on Hugging Face

Cran-May has published 92 GGUF models that ggufmodels.com tracks, across families such as Mistral, Llama and Qwen. The most downloaded are OpenBuddy R10528DistillQwen 72B Preview1, Replete Qwen 2.5 3b CoT RP Q5 K M and XinYuan Qwen2.5 7B 0917 Q4 K M.

The quants Cran-May publishes most often are Q4_K_M (34), Q5_K_M (26), Q4_K_S (9) and IQ4_XS (7). Their Q4_K_M files range from 1.1 to 42.5 GB. Parameter counts run from 66M to 72.7B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has Cran-May published?

92 models are listed here, mainly from the Mistral, Llama and Qwen families. The most downloaded is OpenBuddy R10528DistillQwen 72B Preview1.

Which quants does Cran-May publish?

The most common are Q4_K_M (34 models), Q5_K_M (26 models), Q4_K_S (9 models) and IQ4_XS (7 models).

Keep browsing