Yes — mradermacher/Sancara_text_generation-GGUF fits on RTX 3090 24GB: estimated 1.87 GB (weights + KV cache) against 24 GB.
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.
Yes — mradermacher/Sancara_text_generation-GGUF fits on RTX 3090 24GB: estimated 1.87 GB (weights + KV cache) against 24 GB.
| GPU | Verdict | VRAM |
|---|---|---|
| NVIDIA T4 16GB (free Colab) | Yes | 16 GB |
| NVIDIA L4 24GB | Yes | 24 GB |
| RTX 3060 12GB | Yes | 12 GB |
| RTX 4080 16GB | Yes | 16 GB |
| RTX 3090 24GB | Yes | 24 GB |
| RTX 4090 24GB | Yes | 24 GB |
| A100 40GB | Yes | 40 GB |
| A100 80GB | Yes | 80 GB |
| H100 80GB | Yes | 80 GB |
| Apple M-series 16GB (unified) | Yes | 16 GB |
| Apple M-series 32GB (unified) | Yes | 32 GB |
| Apple M-series 64GB (unified) | Yes | 64 GB |
| Apple M-series 128GB (unified) | Yes | 128 GB |
| CPU / 32GB system RAM | Yes | 32 GB |
| CPU / 64GB system RAM | Yes | 64 GB |
| Repo | Quant | Approx weights | Hosting |
|---|---|---|---|
| bartowski/Qwen_Qwen3-Next-80B-A3B-Thinking-GGUF | unknown | 160 GB | external |
| VesNFF/Qwen3-VL-Embedding-8B-GGUF | q6_k | 6.6 GB | external |
| bartowski/command-a-plus-05-2026-GGUF | unknown | — | external |
| huihui-ai/Huihui-gemma-4-12B-agentic-fable5-abliterated-GGUF | q8_0 | 12.7 GB | external |
| bartowski/p-e-w_gpt-oss-20b-heretic-GGUF | q3_k_s | 8 GB | external |
| crusoeai/Arcee-Agent-GGUF | q3_k_m | — | external |
| mradermacher/Arxh-2.29-12B-it-GGUF | q3_k_m | 5.3 GB | external |
| unsloth/GLM-4.7-Flash-GGUF | q4_k_s | — | hosted ✓ |
Methodology: weights + KV-cache estimate from parameter count, quant precision, and declared context. Not a benchmark; runtimes differ. Data recomputed hourly.