GGUF models by ProjectZLLM

36 GGUF models quantized by ProjectZLLM on Hugging Face. Sizes run from 3.82B to 8.03B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
SF
SFT dna phi b
Sft · ProjectZLLM
Params3.82B
Context128K
Q4_K_M2.3 GB
GGUF
SF
SFT dna phi p8 bs1 r8
Sft · ProjectZLLM
Params3.82B
Context128K
Q4_K_M2.3 GB
GGUF
LL
SFT dna Llama 3.1 8B Instruct 20 r16
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
SFT dna Llama 3.1 8B Instruct 50 r16
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
SF
SFT dna phi p8 bs1
Sft · ProjectZLLM
Params3.82B
Context128K
Q4_K_M2.3 GB
GGUF
SF
SFT dna phi P8
Sft · ProjectZLLM
Params3.82B
Context128K
Q4_K_M2.3 GB
GGUF
SF
SFT dna phi book
Sft · ProjectZLLM
Params3.82B
Context128K
Q4_K_M2.3 GB
GGUF
LL
SFT dna Llama 3.1 8B Instruct 20 r16 b10
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
SFT Llama 3.1 8B Instruct P 2
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
SFT qa Llama 3.1 8B Instruct 20 r16
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
orpo-passive-Llama-3-8B-Instruct-p5000-user_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
orpo-passive-Llama-3-8B-Instruct-prompt-1-2epoch_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
SF
SFT dna phi P
Sft · ProjectZLLM
Params3.82B
Context128K
Q4_K_M2.3 GB
GGUF
LL
SFT Llama 3.1 8B Instruct intent5
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
SFT dka qa Llama 3.1 8B Instruct 20 r16
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
SFT Dk Qa Llama 3.1 8B Instruct Ta
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
orpo-passive-Llama-3-8B-Instruct-user-NoI-15_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
orpo-passive-Llama-3-8B-Instruct-prompt-1-3epoch_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
SFT Llama 3.1 8B Instruct P 1
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
orpo-passive-Llama-3-8B-Instruct-user-NoI-5_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
orpo-passive-Llama-3-8B-Instruct-prompt-1-1epoch_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
SFT qa Llama 3.1 8B Instruct 20 r16 1
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
SFT Dk Qa Llama 3.1 8B Instruct Bc
Llama · ProjectZLLM
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
orpo-passive-Llama-3-8B-Instruct-prompt_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
orpo-passive-Llama-3-8B-Instruct-prompt-1-cos_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
orpo eMailC Llama 3 8B Instruct 50
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
orpo-passive-Llama-3-8B-Instruct-p5000-user-5_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
orpo-passive-Llama-3-8B-Instruct-user-NoI-13_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
orpo-passive-Llama-3-8B-Instruct-user-NoI-25_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
orpo-passive-Llama-3-8B-Instruct-prompt-1-4epoch_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF

About ProjectZLLM on Hugging Face

ProjectZLLM has published 36 GGUF models that ggufmodels.com tracks, across families such as Llama and Sft. The most downloaded are SFT dna phi b, SFT dna phi p8 bs1 r8 and SFT dna Llama 3.1 8B Instruct 20 r16.

The quants ProjectZLLM publishes most often are Q4_K_M (36) and BF16 (36). Their Q4_K_M files range from 2.3 to 4.9 GB. Parameter counts run from 3.82B to 8.03B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has ProjectZLLM published?

36 models are listed here, mainly from the Llama and Sft families. The most downloaded is SFT dna phi b.

Which quants does ProjectZLLM publish?

The most common are Q4_K_M (36 models) and BF16 (36 models).

Keep browsing