GGUF models by epapanita
59 GGUF models quantized by epapanita on Hugging Face. Sizes run from 27M to 24.3B parameters.
WH
Whisper Large v3 Turbo
Whisper · epapanita
Params809M
Context—
Q4_K_M0.5 GB
PA
Parakeet CTC 1.1B
Parakeet · epapanita
Params1.06B
Context—
Q4_K_M0.8 GB
GI
GigaAM v3 E2E-RNN-T
Gigaam · epapanita
Params223M
Context—
Q4_K_M0.2 GB
GI
GigaAM v3 E2E-CTC
Gigaam · epapanita
Params221M
Context—
Q4_K_M0.2 GB
BR
Breeze-ASR-25
Breeze · epapanita
Params1.54B
Context—
Q4_K_M1.0 GB
GR
Granite Speech 4.1 2B NAR
Granite · epapanita
Params2.25B
Context—
Q4_K_M1.6 GB
MI
Voxtral Small 24B
Mistral · epapanita
Params24.3B
Context—
Q4_K_M14.3 GB
MI
Voxtral Mini 3B
Mistral · epapanita
Params4.68B
Context—
Q4_K_M3.0 GB
WH
Whisper Large v2
Whisper · epapanita
Params1.54B
Context—
Q4_K_M1.0 GB
WH
Whisper Tiny (English)
Whisper · epapanita
Params38M
Context—
Q4_K_M0.0 GB
CA
Canary 180M Flash
Canary · epapanita
Params189M
Context—
Q4_K_M0.1 GB
CA
Canary 1B Flash
Canary · epapanita
Params890M
Context—
Q4_K_M0.7 GB
WH
Whisper Small
Whisper · epapanita
Params242M
Context—
Q4_K_M0.2 GB
WH
Whisper Medium (English)
Whisper · epapanita
Params764M
Context—
Q4_K_M0.5 GB
WH
Whisper Large v3
Whisper · epapanita
Params1.54B
Context—
Q4_K_M1.0 GB
GR
Granite Speech 4.1 2B
Granite · epapanita
Params2.31B
Context—
Q4_K_M1.6 GB
QW
Canary-Qwen 2.5B
Qwen · epapanita
Params2.53B
Context—
Q4_K_M1.7 GB
PA
Parakeet Unified EN 0.6B
Parakeet · epapanita
Params618M
Context—
Q4_K_M0.5 GB
WH
Whisper Tiny
Whisper · epapanita
Params38M
Context—
Q4_K_M0.0 GB
WH
Whisper Large
Whisper · epapanita
Params1.54B
Context—
Q4_K_M1.0 GB
PA
Parakeet RNN-T 0.6B
Parakeet · epapanita
Params617M
Context—
Q4_K_M0.5 GB
WH
Whisper Base
Whisper · epapanita
Params73M
Context—
Q4_K_M0.1 GB
GR
Granite Speech 4.1 2B Plus
Granite · epapanita
Params2.11B
Context—
Q4_K_M1.5 GB
GI
GigaAM v3 CTC
Gigaam · epapanita
Params221M
Context—
Q4_K_M0.2 GB
PA
Parakeet TDT 0.6B v3
Parakeet · epapanita
Params627M
Context—
Q4_K_M0.5 GB
CO
Cohere Transcribe
Cohere · epapanita
Params2.05B
Context—
Q4_K_M1.6 GB
PA
Parakeet RNN-T 1.1B
Parakeet · epapanita
Params1.07B
Context—
Q4_K_M0.8 GB
PA
Parakeet TDT-CTC 1.1B
Parakeet · epapanita
Params1.07B
Context—
Q4_K_M0.8 GB
WH
Whisper Base (English)
Whisper · epapanita
Params73M
Context—
Q4_K_M0.1 GB
CO
Cohere Transcribe
Cohere · epapanita
Params2.05B
Context—
Q4_K_M1.6 GB
About epapanita on Hugging Face
epapanita has published 59 GGUF models that ggufmodels.com tracks, across families such as Moonshine, Whisper and Parakeet. The most downloaded are Whisper Large v3 Turbo, Parakeet CTC 1.1B and GigaAM v3 E2E-RNN-T.
The quants epapanita publishes most often are Q8_0 (59), F16 (59), F32 (44) and Q6_K (42). Their Q4_K_M files range from 0.0 to 14.3 GB. Parameter counts run from 27M to 24.3B.
Frequently asked questions
What GGUF models has epapanita published?
59 models are listed here, mainly from the Moonshine, Whisper and Parakeet families. The most downloaded is Whisper Large v3 Turbo.
Which quants does epapanita publish?
The most common are Q8_0 (59 models), F16 (59 models), F32 (44 models) and Q6_K (42 models).