SAVRN Model Hub · DSV4.1-Flash-1017-DERISKED-EXL3-1.61bpw
DSV4.1-Flash-1017-DERISKED-EXL3-1.61bpw GPU Requirements
DSV4.1-Flash-1017-DERISKED-EXL3-1.61bpw needs about 1.0 TB of GPU memory at 16-bit, 517 GB at 8-bit and 258 GB at 4-bit: its 430.5B parameters plus a 20% working margin. The cheapest setup at 16-bit is 5x MI325X from $10.00 an hour, about $7,300 a month around the clock. None of the 9 accelerators the SAVRN Index prices holds it on one card at 16-bit.
Every Accelerator, Every Precision
How many cards of each accelerator the SAVRN Index prices it takes to hold DSV4.1-Flash-1017-DERISKED-EXL3-1.61bpw, and what that many cards cost an hour at the lowest listed on-demand price. Memory needed: 1.0 TB at 16-bit, 517 GB at 8-bit, 258 GB at 4-bit.
| Accelerator | Memory per card | Lowest price per card | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|---|
| H100 Voltage Park |
80 GB | $1.99 | More than 8 | 7 cards $13.93/hr |
4 cards $7.96/hr |
| H200 GMI Cloud |
141 GB | $2.60 | 8 cards $20.80/hr |
4 cards $10.40/hr |
2 cards $5.20/hr |
| B200 Vultr |
180 GB | $3.50 | 6 cards $21.00/hr |
3 cards $10.50/hr |
2 cards $7.00/hr |
| GB200 NVL72 GMI Cloud |
186 GB | $8.00 | 6 cards $48.00/hr |
3 cards $24.00/hr |
2 cards $16.00/hr |
| MI300X Vultr |
192 GB | $1.85 | 6 cards $11.10/hr |
3 cards $5.55/hr |
2 cards $3.70/hr |
| MI325X Vultr |
256 GB | $2.00 | 5 cards $10.00/hr |
3 cards $6.00/hr |
2 cards $4.00/hr |
| B300 Massed Compute |
268 GB | $6.60 | 4 cards $26.40/hr |
2 cards $13.20/hr |
1 card $6.60/hr |
| GB300 NVL72 Verda |
279 GB | $11.17 | 4 cards $44.68/hr |
2 cards $22.34/hr |
1 card $11.17/hr |
| MI355X Vultr |
288 GB | $2.59 | 4 cards $10.36/hr |
2 cards $5.18/hr |
1 card $2.59/hr |
Running It Around the Clock
| Precision | Cheapest setup | Per hour | Per month (730 hours) |
|---|---|---|---|
| 16-bit | 5x MI325X (Vultr) | $10.00 | $7,300 |
| 8-bit | 2x MI355X (Vultr) | $5.18 | $3,781 |
| 4-bit | 1x MI355X (Vultr) | $2.59 | $1,891 |
One copy of the model on rented cards, busy or idle. Serving more users at once takes more copies or more memory for their contexts.
Questions
How much VRAM does DSV4.1-Flash-1017-DERISKED-EXL3-1.61bpw need?
About 1.0 TB at 16-bit; about 517 GB at 8-bit; about 258 GB at 4-bit: the weights plus 20% for the runtime and a short context. A long context needs more.
What is the cheapest GPU setup to run DSV4.1-Flash-1017-DERISKED-EXL3-1.61bpw?
At 16-bit, 5x MI325X from $10.00 an hour, at the lowest on-demand price the SAVRN Index lists.
Can DSV4.1-Flash-1017-DERISKED-EXL3-1.61bpw run on a single H100?
No. An H100 has 80 GB, and DSV4.1-Flash-1017-DERISKED-EXL3-1.61bpw needs 258 GB even at 4-bit, so it takes more than one card.
Memory is the weights at that precision plus 20% for the runtime and a short context. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 20, 2026. Setups beyond eight cards, one server, are not listed.