GGUF models by flyfishstudio
42 GGUF models quantized by flyfishstudio on Hugging Face. Sizes run from 494M to 9.24B parameters. The longest trained context is 128K tokens.
QW
Qwen2.5 3B Instruct Q4 0 4 4
Qwen · flyfishstudio
Params3.09B
Context32K
Smallest1.8 GB
QW
Qwen2.5 3B Instruct Q4 0 4 8
Qwen · flyfishstudio
Params3.09B
Context32K
Smallest1.8 GB
PH
Phi 3.5 Mini instruct_Uncensored
Phi · flyfishstudio
Params3.82B
Context128K
Smallest2.2 GB
GE
Gemma 2 2b It
Gemma · flyfishstudio
Params2.61B
Context8K
Smallest1.6 GB
QW
qwen2-0_5b-instruct
Qwen · flyfishstudio
Params494M
Context32K
Smallest0.4 GB
GE
Gemma 2 9b It
Gemma · flyfishstudio
Params9.24B
Context8K
Smallest5.4 GB
QW
qwen2-0_5b-instruct
Qwen · flyfishstudio
Params494M
Context32K
Smallest0.4 GB
GE
Gemma 2 2b It
Gemma · flyfishstudio
Params2.61B
Context8K
Smallest1.6 GB
PH
Phi 3.5 Mini Instruct
Phi · flyfishstudio
Params3.82B
Context128K
Smallest2.2 GB
GE
Gemma 2 9b It
Gemma · flyfishstudio
Params9.24B
Context8K
Smallest5.4 GB
LL
Meta Llama 3.1 8B Instruct Abliterated
Llama · flyfishstudio
Params8.03B
Context128K
Smallest4.7 GB
LL
yarn llama 2 7b 128k Q4 0 4 4
Llama · flyfishstudio
Params6.74B
Context128K
Smallest3.8 GB
LL
Meta Llama 3.1 8B Instruct Abliterated
Llama · flyfishstudio
Params8.03B
Context128K
Smallest4.7 GB
PH
Phi 3.1 mini 4k instruct Q4 0 4 4
Phi · flyfishstudio
Params3.82B
Context4K
Smallest2.2 GB
GE
gemma 2 2b it v2 Q4 0 4 4
Gemma · flyfishstudio
Params2.61B
Context8K
Smallest1.6 GB
PH
Phi 3.5 Mini instruct_Uncensored
Phi · flyfishstudio
Params3.82B
Context128K
Smallest2.2 GB
RO
rocket 3b Q4 0 4 4
Rocket · flyfishstudio
Params2.8B
Context4K
Smallest1.6 GB
LL
Hermes 3 Llama 3.1 8B
Llama · flyfishstudio
Params8.03B
Context128K
Smallest4.7 GB
OR
orca mini v3 7b Q4 0 4 4
Orca · flyfishstudio
Params6.74B
Context4K
Smallest3.8 GB
GE
Gemma 2 Ataraxy 9B Q4 0 4 4
Gemma · flyfishstudio
Params9.24B
Context8K
Smallest5.4 GB
GE
gemma 2 2b it v2 Q4 0 4 8
Gemma · flyfishstudio
Params2.61B
Context8K
Smallest1.6 GB
PH
Phi 3.1 mini 4k instruct Q4 0 4 8
Phi · flyfishstudio
Params3.82B
Context4K
Smallest2.2 GB
GE
Gemma 2 Ataraxy 9B Q4 0 4 8
Gemma · flyfishstudio
Params9.24B
Context8K
Smallest5.4 GB
MI
openhermes 2.5 mistral 7b Q4 0 4 4
Mistral · flyfishstudio
Params7.24B
Context32K
Smallest4.1 GB
TI
tinyllama 1.1b chat v1.0 Q4 0 4 4
Tinyllama · flyfishstudio
Params1.1B
Context2K
Smallest0.6 GB
OR
orca mini v3 7b Q4 0 4 8
Orca · flyfishstudio
Params6.74B
Context4K
Smallest3.8 GB
QW
Qwen1.5 1.8B Layla v4
Qwen · flyfishstudio
Params1.84B
Context32K
Smallest1.1 GB
LL
llama 2 7b chat Q4 0 4 8
Llama · flyfishstudio
Params6.74B
Context4K
Smallest3.8 GB
PH
Phi 3.5 Mini Instruct
Phi · flyfishstudio
Params3.82B
Context128K
Smallest2.2 GB
QW
Qwen1.5 1.8B Layla v4
Qwen · flyfishstudio
Params1.84B
Context32K
Smallest1.1 GB
About flyfishstudio on Hugging Face
flyfishstudio has published 42 GGUF models that ggufmodels.com tracks, across families such as Llama, Gemma and Qwen. The most downloaded are Qwen2.5 3B Instruct Q4 0 4 4, Qwen2.5 3B Instruct Q4 0 4 8 and Phi 3.5 Mini instruct_Uncensored.
The quants flyfishstudio publishes most often are Q4_0 (42). Parameter counts run from 494M to 9.24B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has flyfishstudio published?
42 models are listed here, mainly from the Llama, Gemma and Qwen families. The most downloaded is Qwen2.5 3B Instruct Q4 0 4 4.
Which quants does flyfishstudio publish?
The most common are Q4_0 (42 models).