No — mradermacher/Poro-34B-chat-OpenAssistant-i1-GGUF needs ~75.05 GB, more than the 24 GB on RTX 3090 24GB. No hosted smaller quant is indexed yet.
Hugging Bay is intentionally crawlable for search engines, answer engines, user-requested AI fetches, frontier AI assistants, and open-source agents. Public pages describe verified open-source AI artifact metadata, provenance, licenses, community trust signals, and selective hosted mirrors with hashes. Hugging Bay does not bypass gated or restricted upstream access controls.
Machine-readable entrypoints: robots.txt, AI search guidance, well-known AI search JSON, AI citation packs, well-known AI citation JSON, llms.txt, llms-full.txt, AI crawler policy, AI bot allowlist, answer-engine manifest, agent manifest, OpenAPI, and indexing status.
No — mradermacher/Poro-34B-chat-OpenAssistant-i1-GGUF needs ~75.05 GB, more than the 24 GB on RTX 3090 24GB. No hosted smaller quant is indexed yet.
| GPU | Verdict | VRAM |
|---|---|---|
| NVIDIA T4 16GB (free Colab) | No | 16 GB |
| NVIDIA L4 24GB | No | 24 GB |
| RTX 3060 12GB | No | 12 GB |
| RTX 4080 16GB | No | 16 GB |
| RTX 3090 24GB | No | 24 GB |
| RTX 4090 24GB | No | 24 GB |
| A100 40GB | No | 40 GB |
| A100 80GB | Tight — close to the limit | 80 GB |
| H100 80GB | Tight — close to the limit | 80 GB |
| Apple M-series 16GB (unified) | No | 16 GB |
| Apple M-series 32GB (unified) | No | 32 GB |
| Apple M-series 64GB (unified) | No | 64 GB |
| Apple M-series 128GB (unified) | Yes | 128 GB |
| CPU / 32GB system RAM | No | 32 GB |
| CPU / 64GB system RAM | No | 64 GB |
| Repo | Quant | Approx weights | Hosting |
|---|---|---|---|
| mradermacher/Poro-34B-chat-OpenAssistant-i1-GGUF | unknown | 68 GB | external |
Methodology: weights + KV-cache estimate from parameter count, quant precision, and declared context. Not a benchmark; runtimes differ. Data recomputed hourly.