SA

Sarashina 13B Finetuned v1

SarashinaGGUF by mradermacherUpdated 2025-07-11
Download on Hugging Face
Parameters13.7B
Context4K
Layers40
Architecturellama
Smallest quant3.3 GB
Quick answer

Sarashina 13B Finetuned v1 needs about 15.6 GB of memory at Q4_K_M (a 8.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 3.3 GB (IQ1_S) to 11.3 GB (Q6_K).

Sarashina 13B Finetuned v1 – Japanese‑English math and technical Q&A

Sarashina 13B Finetuned v1 is a 13.7 billion parameter transformer fine‑tuned for math reasoning and technical queries in Japanese and English. It is released under the MIT license and supports a 4096‑token context window.

Good at

  • Math problem solving
  • Technical question answering
  • Japanese‑English bilingual dialogue

Limits

  • No vision support
  • May hallucinate explanations
  • Requires 8 k context for memory estimates

Best for

  • Academic tutoring
  • Technical documentation assistance
  • Language translation with math context

Who it’s for. Developers and educators seeking a bilingual model for math and technical content. The model is suitable for research and production use where an MIT‑licensed, 13.7 billion parameter LLM is needed.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.3 GB 7.1 GB
Fits Get file →
IQ1_M3.5 GB 7.4 GB
Tight Get file →
IQ2_XXS3.9 GB 7.8 GB
Tight Get file →
IQ2_XS4.3 GB 8.1 GB
Too big Get file →
IQ2_S4.6 GB 8.5 GB
Too big Get file →
Q2_K_S4.9 GB 8.7 GB
Too big Get file →
IQ2_M4.9 GB 8.8 GB
Too big Get file →
Q2_K5.3 GB 9.1 GB
Too big Get file →
IQ3_XXS5.4 GB 9.2 GB
Too big Get file →
IQ3_XS5.8 GB 9.7 GB
Too big Get file →
IQ3_S6.1 GB 10.0 GB
Too big Get file →
Q3_K_S6.1 GB 10.0 GB
Too big Get file →
IQ3_M6.4 GB 10.3 GB
Too big Get file →
Q3_K_M6.8 GB 10.6 GB
Too big Get file →
Q3_K_L7.4 GB 11.2 GB
Too big Get file →
IQ4_XS7.5 GB 11.3 GB
Too big Get file →
IQ4_NL7.9 GB 11.7 GB
Too big Get file →
Q4_07.9 GB 11.7 GB
Too big Get file →
Q4_K_S7.9 GB 11.8 GB
Too big Get file →
Q4_K_M8.4 GB 12.2 GB
Too big Get file →
Q4_18.7 GB 12.5 GB
Too big Get file →
Q5_K_S9.5 GB 13.4 GB
Too big Get file →
Q5_K_M9.8 GB 13.6 GB
Too big Get file →
Q6_K11.3 GB 15.1 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (3.27 GB, 10.5 GB memory). For 12 GB VRAM use Q4_K_M (8.37 GB, 15.6 GB memory). For 16 GB VRAM use Q5_K_M (9.78 GB, 17 GB memory). Estimates are approximate.

What GPU do you need for Sarashina 13B Finetuned v1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ2_S (4.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (8.7 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (11.3 GB file, about 18.5 GB in use).

Which Sarashina 13B Finetuned v1 quant should you choose?

Q4_K_M is the usual starting point for Sarashina 13B Finetuned v1: it balances file size and quality well. Here it is a 8.4 GB file.

If memory is tight, the smallest file is IQ1_S at 3.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13.7B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilySarashina
Licensemit
Downloads (HF)677
Last updated2025-07-11

Frequently asked questions about Sarashina 13B Finetuned v1

How much VRAM does Sarashina 13B Finetuned v1 need?

About 15.6 GB at Q4_K_M with an 8K context window. That is the 8.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Sarashina 13B Finetuned v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sarashina 13B Finetuned v1 GGUF?

It depends on the quant: IQ1_S is 3.3 GB, IQ1_M is 3.5 GB, IQ2_XXS is 3.9 GB, IQ2_XS is 4.3 GB, IQ2_S is 4.6 GB, Q2_K_S is 4.9 GB and 18 more.

What context length does Sarashina 13B Finetuned v1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download Sarashina 13B Finetuned v1 GGUF?

The files are on Hugging Face in the mradermacher/sarashina-13B-finetuned-v1-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Sarashina 13B Finetuned v1 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Sarashina 13B Finetuned v1 on 8 GB VRAM?

Use the IQ1_S quant; it requires about 10.5 GB of VRAM at 8 k context.

Does the model support vision inputs?

No, the model is a text‑only transformer.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of sarashina-13B-finetuned-v1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sarashina models

All Sarashina →

Other medium models

All medium models →