SAVRN Model Hub · DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000
DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000 GPU Requirements
DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000 needs about 526 GB of GPU memory at 16-bit, 263 GB at 8-bit and 131 GB at 4-bit: its 219B parameters plus a 20% working margin. The cheapest setup at 16-bit is 2x MI355X from $5.18 an hour, about $3,781 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 DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000, and what that many cards cost an hour at the lowest listed on-demand price. Memory needed: 526 GB at 16-bit, 263 GB at 8-bit, 131 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 | 7 cards $13.93/hr |
4 cards $7.96/hr |
2 cards $3.98/hr |
| H200 GMI Cloud |
141 GB | $2.60 | 4 cards $10.40/hr |
2 cards $5.20/hr |
1 card $2.60/hr |
| B200 Vultr |
180 GB | $3.50 | 3 cards $10.50/hr |
2 cards $7.00/hr |
1 card $3.50/hr |
| GB200 NVL72 GMI Cloud |
186 GB | $8.00 | 3 cards $24.00/hr |
2 cards $16.00/hr |
1 card $8.00/hr |
| MI300X Vultr |
192 GB | $1.85 | 3 cards $5.55/hr |
2 cards $3.70/hr |
1 card $1.85/hr |
| MI325X Vultr |
256 GB | $2.00 | 3 cards $6.00/hr |
2 cards $4.00/hr |
1 card $2.00/hr |
| B300 Massed Compute |
268 GB | $6.60 | 2 cards $13.20/hr |
1 card $6.60/hr |
1 card $6.60/hr |
| GB300 NVL72 Verda |
279 GB | $10.32 | 2 cards $20.64/hr |
1 card $10.32/hr |
1 card $10.32/hr |
| MI355X Vultr |
288 GB | $2.59 | 2 cards $5.18/hr |
1 card $2.59/hr |
1 card $2.59/hr |
Running It Around the Clock
| Precision | Cheapest setup | Per hour | Per month (730 hours) |
|---|---|---|---|
| 16-bit | 2x MI355X (Vultr) | $5.18 | $3,781 |
| 8-bit | 1x MI355X (Vultr) | $2.59 | $1,891 |
| 4-bit | 1x MI300X (Vultr) | $1.85 | $1,350 |
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 DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000 need?
About 526 GB at 16-bit; about 263 GB at 8-bit; about 131 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 DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000?
At 16-bit, 2x MI355X from $5.18 an hour, at the lowest on-demand price the SAVRN Index lists.
Can DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000 run on a single H100?
No. An H100 has 80 GB, and DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000 needs 131 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 7, 2026. Setups beyond eight cards, one server, are not listed.