GGUF models by PrunaAI

95 GGUF models quantized by PrunaAI on Hugging Face. Sizes run from 10M to 141B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
BCCard Llama 3 Kor BCCard Finance 8B GGUF smashed
Llama · PrunaAI
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
AD
AdaptLLM finance chat GGUF smashed
Adaptllm · PrunaAI
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
MI
Mistral 7B v0.3 GGUF smashed
Mistral · PrunaAI
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
GE
google gemma 2 2b GGUF smashed
Gemma · PrunaAI
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
LL
Llama3 ChatQA 1.5 8B GGUF smashed
Llama · PrunaAI
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
CA
camel ai CAMEL 13B Role Playing Data GGUF smashed
Camel · PrunaAI
Params13B
Context2K
Q4_K_M7.9 GB
Roleplay
IN
InternLM2
InternLM · PrunaAI
Params19.9B
Context32K
Q4_K_M12.0 GB
GGUF
CO
CodeQwen1.5 7B Chat GGUF smashed
Codeqwen · PrunaAI
Params7.25B
Context64K
Q4_K_M4.7 GB
GGUF
MI
Codestral 22B v0.1
Mistral · PrunaAI
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
PH
microsoft Phi 3 medium 4k instruct GGUF smashed
Phi · PrunaAI
Params14B
Context4K
Q4_K_M8.6 GB
GGUF
YO
yodayo ai nephra v1.0 GGUF smashed
Yodayo · PrunaAI
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen2.5 7B
Qwen · PrunaAI
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
LL
pkupie lawyer llama 13b beta1.0 GGUF smashed
Llama · PrunaAI
Params13B
Context2K
Q4_K_M0.0 GB
GGUF
VI
Virtuoso Medium
Virtuoso · PrunaAI
Params10M
Context128K
Q4_K_M0.0 GB
Tool use
DC
ThisIsATest dclm id 410m GGUF smashed
Dclm · PrunaAI
Params405M
Context2K
Q4_K_M0.3 GB
GGUF
LL
AlfredPros CodeLlama 7b Instruct Solidity GGUF smashed
Llama · PrunaAI
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
HI
HiroseKoichi L3 8B Lunar Stheno GGUF smashed
Hirosekoichi · PrunaAI
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen2.5 0.5B
Qwen · PrunaAI
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
LL
gradientai Llama 3 8B Instruct Gradient 4194k GGUF smashed
Llama · PrunaAI
Params8.03B
Context1K
Q4_K_M4.9 GB
GGUF
LL
LoneStriker Meta Llama 3 70B Instruct 2.25bpw h6 exl2 GGUF smashed
Llama · PrunaAI
Params13M
Context8K
Q4_K_M0.0 GB
GGUF
GI
Collinslm gita text generation gpt2 GGUF smashed
Gita · PrunaAI
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
MA
Gustavosta MagicPrompt Stable Diffusion GGUF smashed
Magicprompt · PrunaAI
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
WI
Wizard Vicuna 30B Uncensored
Wizard · PrunaAI
Params30B
Context2K
Q4_K_M0.0 GB
GGUF
GI
naveenkumarCH gita text generation gpt2 GGUF smashed
Gita · PrunaAI
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
CH
jpacifico Chocolatine 14B Instruct DPO v1.2 GGUF smashed
Chocolatine · PrunaAI
Params14B
Context4K
Q4_K_M8.6 GB
GGUF
RU
impossibleexchange run85 GGUF smashed
Run · PrunaAI
Params7.72B
Context128K
Q4_K_M4.7 GB
GGUF
FA
Falcon
Falcon · PrunaAI
Params11.1B
Context2K
Q4_K_M6.8 GB
GGUF
MI
Mistral 7B Instruct v0.3 GGUF smashed
Mistral · PrunaAI
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
LL
tyzhu tiny LLaMA 1b 8k intramask cc 8k iter 320000 ckpt step 40000 hf GGUF smashed
Llama · PrunaAI
Params1.1B
Context8K
Q4_K_M0.7 GB
GGUF
PH
microsoft Phi 3 medium 128k instruct GGUF smashed
Phi · PrunaAI
Params14B
Context128K
Q4_K_M8.6 GB
GGUF

Keep browsing