GGUF models by antoste
48 GGUF models quantized by antoste on Hugging Face. Sizes run from 134M to 18.5B parameters. The longest trained context is 1024K tokens.
QW
Qwen2 7B Instruct
Qwen · antoste
Params7.62B
Context32K
Smallest3.0 GB
PH
Phi 3 Medium 128k Instruct
Phi · antoste
Params14B
Context128K
Smallest9.6 GB
GP
Gpt2 Xl
Gpt · antoste
Params1.64B
Context1K
Smallest1.4 GB
GE
Gemma 2 2b It
Gemma · antoste
Params2.61B
Context8K
Smallest1.2 GB
MA
Magiq-3
Magiq · antoste
Params18.5B
Context32K
Smallest6.8 GB
ST
StableLM 2 1.6B Chat
Stablelm · antoste
Params1.64B
Context4K
Smallest0.9 GB
GE
Gemma 2 2b
Gemma · antoste
Params2.61B
Context8K
Smallest1.4 GB
QW
Qwen2 1.5B Ita Q8 0
Qwen · antoste
Params1.54B
Context32K
Smallest1.6 GB
MA
Mamba 2.8b Hf
Mamba · antoste
Params2.77B
Context1024K
Smallest3.3 GB
SE
SeewebLLM it Q4 K M
Seewebllm · antoste
Params6.74B
Context4K
Q4_K_M4.1 GB
GP
Gpt2 Xl
Gpt · antoste
Params1.64B
Context1K
Smallest1.7 GB
GE
Gemma 2 2b
Gemma · antoste
Params2.61B
Context8K
Smallest1.2 GB
LO
Loquace 7B Q3 K S
Loquace · antoste
Params7.22B
Context2K
Smallest3.9 GB
BL
Bloom 1b7
Bloom · antoste
Params2.24B
Context4K
Q4_K_M1.5 GB
MA
Mamba 2.8b Hf
Mamba · antoste
Params2.77B
Context1024K
Smallest1.7 GB
LL
Llama 3.1 8B Italian SAVA
Llama · antoste
Params7.25B
Context128K
Smallest3.8 GB
ST
StableLM 2 1.6B Chat
Stablelm · antoste
Params1.64B
Context4K
Smallest1.0 GB
MA
Mamba 2.8b Hf
Mamba · antoste
Params2.77B
Context1024K
Smallest2.0 GB