SAVRN Model Hub · Llama-3.3-70B-Instruct
Llama-3.3-70B-Instruct GPU Requirements
Llama-3.3-70B-Instruct needs about 169 GB of GPU memory at 16-bit, 84.7 GB at 8-bit and 42.3 GB at 4-bit: its 70.6B parameters plus a 20% working margin. The cheapest setup at 16-bit is 1x MI300X from $1.85 an hour, about $1,350 a month around the clock. 7 of the 9 accelerators the SAVRN Index prices hold it on one card at 16-bit: B200, GB200 NVL72, B300, GB300 NVL72, MI300X, MI325X, MI355X.
Every Accelerator, Every Precision
How many cards of each accelerator the SAVRN Index prices it takes to hold Llama-3.3-70B-Instruct, and what that many cards cost an hour at the lowest listed on-demand price. Memory needed: 169 GB at 16-bit, 84.7 GB at 8-bit, 42.3 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 | 3 cards $5.97/hr |
2 cards $3.98/hr |
1 card $1.99/hr |
| H200 GMI Cloud |
141 GB | $2.60 | 2 cards $5.20/hr |
1 card $2.60/hr |
1 card $2.60/hr |
| B200 Vultr |
180 GB | $3.50 | 1 card $3.50/hr |
1 card $3.50/hr |
1 card $3.50/hr |
| GB200 NVL72 GMI Cloud |
186 GB | $8.00 | 1 card $8.00/hr |
1 card $8.00/hr |
1 card $8.00/hr |
| MI300X Vultr |
192 GB | $1.85 | 1 card $1.85/hr |
1 card $1.85/hr |
1 card $1.85/hr |
| MI325X Vultr |
256 GB | $2.00 | 1 card $2.00/hr |
1 card $2.00/hr |
1 card $2.00/hr |
| B300 Massed Compute |
268 GB | $6.60 | 1 card $6.60/hr |
1 card $6.60/hr |
1 card $6.60/hr |
| GB300 NVL72 Verda |
279 GB | $8.89 | 1 card $8.89/hr |
1 card $8.89/hr |
1 card $8.89/hr |
| MI355X Vultr |
288 GB | $2.59 | 1 card $2.59/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 | 1x MI300X (Vultr) | $1.85 | $1,350 |
| 8-bit | 1x MI300X (Vultr) | $1.85 | $1,350 |
| 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 Llama-3.3-70B-Instruct need?
About 169 GB at 16-bit; about 84.7 GB at 8-bit; about 42.3 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 Llama-3.3-70B-Instruct?
At 16-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand price the SAVRN Index lists.
Can Llama-3.3-70B-Instruct run on a single H100?
Yes at 4-bit: an H100 has 80 GB and Llama-3.3-70B-Instruct needs 42.3 GB at 4-bit.
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 Sep 18, 2026. Setups beyond eight cards, one server, are not listed.