SAVRN Model Hub · dolphin-2.9.1-yi-1.5-34b
dolphin-2.9.1-yi-1.5-34b GPU Requirements
dolphin-2.9.1-yi-1.5-34b needs about 82.5 GB of GPU memory at 16-bit, 41.3 GB at 8-bit and 20.6 GB at 4-bit: its 34.4B 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. 8 of the 9 accelerators the SAVRN Index prices hold it on one card at 16-bit: H200, 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 dolphin-2.9.1-yi-1.5-34b, and what that many cards cost an hour at the lowest listed on-demand price. Memory needed: 82.5 GB at 16-bit, 41.3 GB at 8-bit, 20.6 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 | 2 cards $3.98/hr |
1 card $1.99/hr |
1 card $1.99/hr |
| H200 GMI Cloud |
141 GB | $2.60 | 1 card $2.60/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.
Memory at Longer Context
Every token in a sequence keeps a key and a value in every layer. From dolphin-2.9.1-yi-1.5-34b's published configuration, that cache adds this much at 16-bit for one sequence:
| Context | Key/value cache | Total with weights | Cheapest setup |
|---|---|---|---|
| 4,096 tokens | 1 GB | 83.5 GB | 1x MI300X $1.85/hr |
| 8,192 tokens (full) | 2 GB | 84.5 GB | 1x MI300X $1.85/hr |
An estimate from layers, key/value heads and head size, assuming full attention in every layer. Runtimes that quantize or page the cache use less.
Questions
How much VRAM does dolphin-2.9.1-yi-1.5-34b need?
About 82.5 GB at 16-bit; about 41.3 GB at 8-bit; about 20.6 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 dolphin-2.9.1-yi-1.5-34b?
At 16-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand price the SAVRN Index lists.
Can dolphin-2.9.1-yi-1.5-34b run on a single H100?
Yes at 8-bit, 4-bit: an H100 has 80 GB and dolphin-2.9.1-yi-1.5-34b needs 41.3 GB at 8-bit.
How much memory does dolphin-2.9.1-yi-1.5-34b need at its full context length?
About 84.5 GB at 16-bit for one 8,192-token sequence: 82.5 GB for the weights and margin plus 2 GB of key/value cache, estimated from its published configuration.
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.