discovered · 13 variants · 0 roots
| variant | kind | quant | vRAM | dl | root |
|---|---|---|---|---|---|
| whisper-large-v3-quantized.w4a16 | int4 | int4 | 3,208 | openai/whisper-large-v3 | |
| whisper-large-v3-turbo-quantized.w4a16 | int4 | int4 | 2,913 | openai/whisper-large-v3-turbo | |
| whisper-large-v3-FP8-dynamic | fp8 | fp8 | 2,382 | openai/whisper-large-v3 | |
| whisper-large-v3-quantized.w8a8 | original | bf16 | 2,307 | openai/whisper-large-v3 | |
| whisper-large-v3-turbo-FP8-dynamic | fp8 | fp8 | 1,323 | openai/whisper-large-v3-turbo | |
| whisper-large-v3-turbo-quantized.w8a8 | original | bf16 | 1,213 | openai/whisper-large-v3-turbo | |
| whisper-small-quantized.w8a8 | original | bf16 | 969 | openai/whisper-small | |
| Voxtral-Mini-3B-2507-FP8-dynamic | fp8 | fp8 | 854 | mistralai/Voxtral-Mini-3B-2507 | |
| Voxtral-Small-24B-2507-FP8-dynamic | fp8 | fp8 | 392 | mistralai/Voxtral-Small-24B-2507 | |
| gemma-3n-E4B-it-FP8-dynamic | fp8 | fp8 | 229 | google/gemma-3n-E4B-it | |
| whisper-large-v2-FP8-Dynamic | fp8 | fp8 | 60 | openai/whisper-large | |
| Voxtral-Mini-4B-Realtime-2602 | original | bf16 | 23 | mistralai/Voxtral-Mini-4B-Realtime-2602 | |
| nemotron-speech-streaming-en-0.6b | original | bf16 | 15 | nvidia/nemotron-speech-streaming-en-0.6b |