GGUF models by macadeliccc

42 GGUF models quantized by macadeliccc on Hugging Face. Sizes run from 3.21B to 69B parameters. The longest trained context is 195K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
laser dolphin mixtral 2x7b dpo
Mistral · macadeliccc
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
WE
WestLake 7B v2 laser truthy dpo
Westlake · macadeliccc
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MA
magistrate 3.2 3b it
Magistrate · macadeliccc
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
SO
SOLAR 10.7b Instruct truthy dpo
Solar · macadeliccc
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
LL
CodeLlama 70b Instruct hf
Llama · macadeliccc
Params69B
Context4K
Q4_K_M41.4 GB
Coding
ST
dolphincoder starcoder2 15b
StarCoder · macadeliccc
Params16B
Context16K
Q4_K_M9.9 GB
Coding
LL
CodeLlama 70b Python hf
Llama · macadeliccc
Params69B
Context4K
Q4_K_M41.4 GB
Coding
MI
LiberatedHermes 2 Pro Mistral 7B
Mistral · macadeliccc
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
AI
airoboros 34b 3.2
Airoboros · macadeliccc
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
LL
Opus Samantha Llama 3 8B
Llama · macadeliccc
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
PI
piccolo 8x7b
Piccolo · macadeliccc
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
LL
CodeLlama 34b Python hf
Llama · macadeliccc
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
LL
CodeLlama 13b Python hf
Llama · macadeliccc
Params13B
Context16K
Q4_K_M7.9 GB
Coding
PH
dolphin-2.9.2-Phi-3-Medium
Phi · macadeliccc
Params14B
Context4K
Q4_K_M8.4 GB
CodingTool use
LA
Laser WestLake 2x7b
Laser · macadeliccc
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
LL
CodeLlama 7b Python hf
Llama · macadeliccc
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
MI
dolphin-2.9.3-mistral-7B-32k
Mistral · macadeliccc
Params7.25B
Context32K
Q4_K_M4.4 GB
CodingTool use
OR
Orpo GutenLlama 3 8B v2
Orpo · macadeliccc
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
AI
airoboros 9b 3.2
Airoboros · macadeliccc
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
DO
dolphin 2.8 experiment26 7b
Dolphin · macadeliccc
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MB
MBX 7B v3 DPO
Mbx · macadeliccc
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SA
samantha 1.1 westlake 7b
Samantha · macadeliccc
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SE
Severus WestLake 2x7B v2
Severus · macadeliccc
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
PI
piccolo 4x7b
Piccolo · macadeliccc
Params24.2B
Context32K
Q4_K_M14.6 GB
GGUF
YI
dolphin-2.9.3-Yi-1.5-34B-32k
Yi · macadeliccc
Params34.4B
Context32K
Q4_K_M20.7 GB
CodingTool use
MO
MonarchLake 7B
Monarchlake · macadeliccc
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Mistral 7B v0.2 OpenHermes
Mistral · macadeliccc
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
LL
Llama3 ChatQA 1.5 8B
Llama · macadeliccc
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
AL
AlphaHitchhiker v2
Alphahitchhiker · macadeliccc
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SO
SOLAR 10.7b Instruct dpo
Solar · macadeliccc
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF

About macadeliccc on Hugging Face

macadeliccc has published 42 GGUF models that ggufmodels.com tracks, across families such as Llama, Mistral and Solar. The most downloaded are laser dolphin mixtral 2x7b dpo, WestLake 7B v2 laser truthy dpo and magistrate 3.2 3b it.

The quants macadeliccc publishes most often are Q5_K_M (38), Q4_K_M (37), Q8_0 (33) and Q2_K (33). Their Q4_K_M files range from 2.0 to 41.4 GB. Parameter counts run from 3.21B to 69B, and the longest trained context window is 195K tokens.

Frequently asked questions

What GGUF models has macadeliccc published?

42 models are listed here, mainly from the Llama, Mistral and Solar families. The most downloaded is laser dolphin mixtral 2x7b dpo.

Which quants does macadeliccc publish?

The most common are Q5_K_M (38 models), Q4_K_M (37 models), Q8_0 (33 models) and Q2_K (33 models).

Keep browsing