Pythia 70M Deduped
Pythia 70M Deduped is EleutherAI's language model. A lightweight 70M-parameter LLM from EleutherAI's Pythia suite trained on a globally deduplicated Pile dataset, suited for interpretability research at small scale.
| Specifications | |
|---|---|
eleutherai-pythia-70m-deduped | |
| Language | |
| Active | |
| EleutherAI | |
| Text | |
| Text | |
| 0.07B | |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host Pythia 70M Deduped, ranked by cheapest on-demand price. The model needs about 0 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| g6f.large |  AWS | L4 | 3 GB | $0.202/hr | us-east-1 | |
| Standard_NV4as_v4 |  Azure | AMD Radeon Instinct MI25 | 16 GB | $0.233/hr | westus2 | |
| g6f.xlarge | AWS | L4 | 3 GB | $0.237/hr | us-east-1 | |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Pythia 70M Deduped | — | — | — | — | Current |
| Pythia 12B | — | 2K | $0.200 | $0.200 | Available |
| Pythia 160M Deduped | — | — | — | — | Available |