Open-weight model
bert-base-uncased-pnn-d50-int8-j21
by Primeneural PrimeNeural/bert-base-uncased-pnn-d50-int8-j21
bert-base-uncased-pnn-d50-int8-j21 is an open-weight model from Primeneural, released under other. It has 79M parameters. At 16-bit it needs about 0.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve bert-base-uncased-pnn-d50-int8-j21 (79M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 21, 2026.
bert-base-uncased-pnn-d50-int8-j21 on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- PrimeNeural/bert-base-uncased-pnn-d50-int8-j21
- Publisher
- Primeneural
- Task
- Not stated by the source
- Modality
- Other
- Library
- pnn
- Parameters
- 79M parameters
- Languages
- pnn
- Revision
- fcaea4c8f1773d4a29f809857eba468c334503a2
- First published
- 2026-10-21
- Last updated
- 2026-10-21
License and Download
- License
- other
- Access
- Open weights, no gate
Released by Primeneural through its official repository on Hugging Face.
Built From
- Derived from google-bert/bert-base-uncased
- Quantized from google-bert/bert-base-uncased
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About bert-base-uncased-pnn-d50-int8-j21
How much GPU memory does bert-base-uncased-pnn-d50-int8-j21 need?
About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (79M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run bert-base-uncased-pnn-d50-int8-j21 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What license is bert-base-uncased-pnn-d50-int8-j21 released under?
other, as its publisher declares it. Read the license text before commercial use.