mradermacher/sarashina2-70b-GGUF

Hugging Bay has hosted the mradermacher/sarashina2-70b-GGUF model, a 445.1 GB quantized version of the sbintuitions/sarashina2-70b base model under the MIT license, with 2 of 15 files verified and scanned. The model supports Japanese and English and is compatible with local runners like Ollama and LM Studio, though it lacks community reviews and benchmarks.

mradermacher/sarashina2-70b-GGUF mradermacher/sarashina2-70b-GGUF: Model from Hugging Face for llm: mradermacher/sarashina2-70b-GGUF · transformers License: mit. 2 Hugging Bay hosted files. Scan: passed. - License - mit - Size - 445.1 GB - Demand - 2 mirror requests - Trust - Verified 28/100 - Trusted download - Verified hosted files - Run fit - Local-run friendly with quantized files: 8-16 GB RAM/VRAM for many quantized or medium checkpoints - Files - 2 hosted / 15 total - Scan status - passed - Hosting status - partial - Upstream - mradermacher/sarashina2-70b-GGUF - Declared license - mit - Pipeline - general - Library - transformers - Base model - sbintuitions/sarashina2-70b - Task categories - general - Languages - ja, en - File hints - 15 upstream file samples About this artifact External Hugging Face catalog record for mradermacher/sarashina2-70b-GGUF. Library: transformers. Languages: ja, en. Base model: sbintuitions/sarashina2-70b. Popularity signal at import: 19 downloads and 0 likes. Files are listed for discovery and verification context; Hugging Bay serves local downloads only after explicit mirror review, scanning, hashing, and signing. Trusted download Verified hosted files. Hugging Bay hosts reviewed files with SHA-256 hashes and a signed manifest. - Hosted files - 2 of 15 - Reviewed peer-assisted fallbacks - 0 - Download plan Download-plan JSON /api/artifacts/hf-model-mradermacher-sarashina2-70b-gguf/download-plan - Trust bundle Trust-bundle JSON /api/trust-bundles/hf-model-mradermacher-sarashina2-70b-gguf - Review summary Review-summary JSON /api/artifacts/hf-model-mradermacher-sarashina2-70b-gguf/review-summary - Distribution Reviewed peer-fallback JSON /api/artifacts/hf-model-mradermacher-sarashina2-70b-gguf/distribution - .gitattributes - 2.3 KB - sha256 3ce6bc8e117505a897eaba1b44756e62691db110f2a77094a62780d9742344ef - README.md - 3.4 KB - sha256 fe1f13a6468990cca427dea37f7f5f3a3f94ba40fe08f67a56fd80e30d78bc91 Can I run this? Local-run friendly with quantized files. 8-16 GB RAM/VRAM for many quantized or medium checkpoints. Prefer GGUF, safetensors, ONNX, or MLX files and verify the manifest before loading. - Estimated footprint - 445.1 GB - Suggested runners - Ollama, LM Studio, llama.cpp, Transformers, vLLM - Runtime files - 8 - Local kit Local run kit /local-kit/hf-model-mradermacher-sarashina2-70b-gguf - sarashina2-70b.IQ4 XS.gguf - 35.4 GB - sarashina2-70b.Q2 K.gguf - 24.3 GB - sarashina2-70b.Q3 K L.gguf - 34.3 GB - sarashina2-70b.Q3 K M.gguf - 31.7 GB - sarashina2-70b.Q3 K S.gguf - 28.5 GB - sarashina2-70b.Q4 K M.gguf - 39.3 GB - sarashina2-70b.Q4 K S.gguf - 37.3 GB - sarashina2-70b.Q5 K M.gguf - 46.2 GB - License: pass - mit - Provenance: pass - mradermacher/sarashina2-70b-GGUF - Scan: pass - passed - Hosted files: pass - 2/15 hosted - Signed manifest: pass - final manifest available - Community: warn - no reviews yet - Benchmarks: warn - no benchmark evidence Machine-readable card Open interactive artifact page / /artifact/hf-model-mradermacher-sarashina2-70b-gguf