SAVRN Model Hub · acquisition_generator_AS_confidence_alpaca_llama8b
acquisition_generator_AS_confidence_alpaca_llama8b GPU Requirements
acquisition_generator_AS_confidence_alpaca_llama8b needs about 35.4 GB of GPU memory at 16-bit, 17.7 GB at 8-bit and 8.9 GB at 4-bit: its 14.8B 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. Every one 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 acquisition_generator_AS_confidence_alpaca_llama8b, and what that many cards cost an hour at the lowest listed on-demand price. Memory needed: 35.4 GB at 16-bit, 17.7 GB at 8-bit, 8.9 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 | 1 card $1.99/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 | $11.94 | 1 card $11.94/hr |
1 card $11.94/hr |
1 card $11.94/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 acquisition_generator_AS_confidence_alpaca_llama8b'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 | 0.8 GB | 36.2 GB | 1x MI300X $1.85/hr |
| 32,768 tokens (full) | 6.4 GB | 41.8 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 acquisition_generator_AS_confidence_alpaca_llama8b need?
About 35.4 GB at 16-bit; about 17.7 GB at 8-bit; about 8.9 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 acquisition_generator_AS_confidence_alpaca_llama8b?
At 16-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand price the SAVRN Index lists.
Can acquisition_generator_AS_confidence_alpaca_llama8b run on a single H100?
Yes at 16-bit, 8-bit, 4-bit: an H100 has 80 GB and acquisition_generator_AS_confidence_alpaca_llama8b needs 35.4 GB at 16-bit.
How much memory does acquisition_generator_AS_confidence_alpaca_llama8b need at its full context length?
About 41.8 GB at 16-bit for one 32,768-token sequence: 35.4 GB for the weights and margin plus 6.4 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 Oct 22, 2026. Setups beyond eight cards, one server, are not listed.