LL

PersianSciQA LLaMA 13B i1

LlamaGGUF by mradermacherUpdated 2025-12-23
Download on Hugging Face
Parameters13.3B
Context4K
Layers40
Architecturellama
Smallest quant0.0 GB
Quick answer

PersianSciQA LLaMA 13B i1 needs about 15.3 GB of memory at Q4_K_M (a 8.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 0.0 GB to 10.9 GB (Q6_K).

PersianSciQA LLaMA 13B i1 – extractive QA on Persian scientific texts

This model is a fine‑tuned 13.3 b Llama that answers questions strictly from a given Persian scientific context. It outputs concise answers or the exact string "CANNOT_ANSWER" when the context lacks the needed information. The model uses a 4096‑token context window.

Good at

  • Extractive question answering
  • Strictly context‑based responses
  • CANNOT_ANSWER fallback

Limits

  • No vision support
  • Apache‑2.0 license
  • Requires 4096‑token context

Best for

  • Academic research assistants
  • Scientific document QA
  • Data extraction from Persian texts

Who it’s for. Researchers and developers needing reliable, context‑only answers from Persian scientific literature. The model is suitable for integration into question‑answering pipelines where faithfulness to the source is critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.9 GB
Fits Get file →
IQ1_S3.1 GB 6.9 GB
Fits Get file →
IQ1_M3.3 GB 7.1 GB
Fits Get file →
IQ2_XXS3.7 GB 7.5 GB
Tight Get file →
IQ2_XS4.0 GB 7.9 GB
Tight Get file →
IQ2_S4.4 GB 8.2 GB
Too big Get file →
Q2_K_S4.6 GB 8.5 GB
Too big Get file →
IQ2_M4.7 GB 8.5 GB
Too big Get file →
Q2_K5.0 GB 8.9 GB
Too big Get file →
IQ3_XXS5.1 GB 9.0 GB
Too big Get file →
IQ3_XS5.6 GB 9.4 GB
Too big Get file →
IQ3_S5.9 GB 9.7 GB
Too big Get file →
Q3_K_S5.9 GB 9.7 GB
Too big Get file →
IQ3_M6.2 GB 10.0 GB
Too big Get file →
Q3_K_M6.5 GB 10.4 GB
Too big Get file →
Q3_K_L7.1 GB 11.0 GB
Too big Get file →
IQ4_XS7.2 GB 11.0 GB
Too big Get file →
IQ4_NL7.6 GB 11.4 GB
Too big Get file →
Q4_07.6 GB 11.5 GB
Too big Get file →
Q4_K_S7.6 GB 11.5 GB
Too big Get file →
Q4_K_M8.1 GB 11.9 GB
Too big Get file →
Q4_18.4 GB 12.2 GB
Too big Get file →
Q5_K_S9.2 GB 13.1 GB
Too big Get file →
Q5_K_M9.5 GB 13.3 GB
Too big Get file →
Q6_K10.9 GB 14.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (3.05 GB, 10.3 GB memory) or IQ1_M (3.29 GB, 10.5 GB memory). For 12 GB VRAM, Q3_K_M (6.53 GB, 13.7 GB memory) or Q4_K_M (8.08 GB, 15.3 GB memory) are suitable. Larger VRAM allows higher‑quality quants such as Q5_K_M (9.46 GB, 16.7 GB memory).

What GPU do you need for PersianSciQA LLaMA 13B i1?

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: the best quant that fits is the main file (0.0 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_M (4.7 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (8.4 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (10.9 GB file, about 18.1 GB in use).

Which PersianSciQA LLaMA 13B i1 quant should you choose?

Q4_K_M is the usual starting point for PersianSciQA LLaMA 13B i1: it balances file size and quality well. Here it is a 8.1 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13.3B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licenseapache-2.0
Downloads (HF)1,277
Last updated2025-12-23

Frequently asked questions about PersianSciQA LLaMA 13B i1

How much VRAM does PersianSciQA LLaMA 13B i1 need?

About 15.3 GB at Q4_K_M with an 8K context window. That is the 8.1 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 PersianSciQA LLaMA 13B i1 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of PersianSciQA LLaMA 13B i1 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.1 GB, IQ1_M is 3.3 GB, IQ2_XXS is 3.7 GB, IQ2_XS is 4.0 GB, IQ2_S is 4.4 GB and 19 more.

What context length does PersianSciQA LLaMA 13B i1 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 PersianSciQA LLaMA 13B i1 GGUF?

The files are on Hugging Face in the mradermacher/PersianSciQA-LLaMA-13B-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 PersianSciQA LLaMA 13B i1 use?

Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quants, which require about 10.3–10.5 GB of VRAM at 8k context.

Does the model support vision or image input?

No, the model is purely text‑based and does not process images.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of PersianSciQA-LLaMA-13B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →