Skip to main content

AI models that run on this device.

Two small chat models run in a computer’s browser here; every other model is a file you download.

mradermacher/sarashina2-70b-GGUF mirror metadata

mradermacher/sarashina2-70b-GGUF has 0 hosted file records out of 13. This inventory does not establish mirror completeness, bundle verification, or runtime readiness.

Task
general
Size
477.9 GB
Recommended file
42.2 GB (Q4_K_M) — sarashina2-70b.Q4_K_M.gguf
Parameters
70B
Files
0 hosted of 13 listed
Download
Downloadable files: 0 confirmed
Added to Hugging Bay
Updated at source

We can’t check the fit — we don’t know your machine.

Check my machine (two questions)

We don’t have your machine’s specs, so no check ran and no verdict is shown. Answer two quick questions and we’ll estimate, from the memory you tell us, whether it fits your machine. Or skip it — you can still download; fit isn’t checked.

Download this program

Files withheld — not faked.

sarashina2-70b.Q4_K_M.gguf · 42.2 GB

Other files (for experts)
  • sarashina2-70b.IQ4_XS.gguf · 38.0 GB
  • sarashina2-70b.Q2_K.gguf · 26.1 GB
  • sarashina2-70b.Q3_K_L.gguf · 36.9 GB
  • sarashina2-70b.Q3_K_M.gguf · 34.0 GB
  • sarashina2-70b.Q3_K_S.gguf · 30.6 GB
  • sarashina2-70b.Q4_K_S.gguf · 40.0 GB
  • sarashina2-70b.Q5_K_M.gguf · 49.6 GB
  • sarashina2-70b.Q5_K_S.gguf · 48.3 GB
  • sarashina2-70b.Q6_K.gguf.part1of2 · 29.0 GB
  • sarashina2-70b.Q6_K.gguf.part2of2 · 28.5 GB
  • sarashina2-70b.Q8_0.gguf.part1of2 · 37.6 GB
  • sarashina2-70b.Q8_0.gguf.part2of2 · 36.9 GB

FAQ

What is this model?

mradermacher/sarashina2-70b-GGUF is an open-weights language model for general published by mradermacher, added to Hugging Bay Jun 30, 2026. Model from Hugging Face for llm: mradermacher/sarashina2-70b-GGUF · transformers

Can I use it commercially?

It is released under the mit license. Commercial use is allowed. Permissive open license: commercial use, modification, and redistribution are permitted.

How big is it?

mradermacher/sarashina2-70b-GGUF has 70B parameters. The total download is 477.9 GB, which includes 9 alternative weight variants; the recommended download, sarashina2-70b.Q4_K_M.gguf (Q4_K_M), is 42.2 GB.

What can I download here?

This model is listed, but we haven't confirmed its download files, so we won't offer a download button we can't stand behind. The record lists 13 files.

File checks and computer fit
File pattern scans

Automated file-pattern scans flagged nothing — not a safety guarantee. The machine-readable verdict is at /api/artifacts/hf-model-mradermacher-sarashina2-70b-gguf/safety on Hugging Bay.

Will mradermacher/sarashina2-70b-GGUF run on my computer?

We can’t check the fit — we don’t know your machine. We don’t have your machine’s specs, so no check ran and no verdict is shown. Answer two quick questions and we’ll estimate, from the memory you tell us, whether it fits your machine. Or skip it — you can still download; fit isn’t checked.

Mirror metadata

Hosted GGUF, safetensors, ONNX, tokenizer, config, and model-card files are listed one by one. A file list and size do not prove a complete kit or working run.

Hosting status
blocked
Hosted files
0 of 13
Download completeness
File inventory only - Individually hashed hosted files may be available, but bundle completeness, verification, and runtime state are unknown.
Demand capture
available
Run status
unknown

No Hugging Bay-hosted files are public yet. Use the mirror request API for reviewed hosting demand.

Mirror metadata API Hosted file inventory API Hosted model file metadata

Request reviewed hosting with POST /api/artifacts/hf-model-mradermacher-sarashina2-70b-gguf/mirror-request. Include desired files when you need a specific GGUF, safetensors, tokenizer, config, or ONNX path.

Evidence details

Demand
2 mirror requests
Trust
Unknown
Run fit
Unknown: canonical-snapshot-missing
Scan status
passed
Executable state
unknown
Evidence timestamp
unknown
Declared license
mit
Pipeline
general
Library
transformers
Base model
sbintuitions/sarashina2-70b
Task categories
general
Languages
ja, en
File hints
15 upstream file samples