IB

ibnsina-llm/ibnsina-3b-v21h

IbnsinaGGUF by ibnsina-llmUpdated 2026-09-10
Download on Hugging Face
Parameters3B
Context2K
Layers40
Architectureqwen3
Smallest quant1.8 GB
Quick answer

ibnsina-llm/ibnsina-3b-v21h needs about 3.0 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.8 GB (Q4_K_M) to 6.0 GB (BF16).

ibnsina-llm/ibnsina-3b-v21h is a 3B-parameter Ibnsina model in GGUF format, quantized by ibnsina-llm. Its trained context length is 2K tokens. The repository has 3 quant files, from 1.8 GB (Q4_K_M) to 6.0 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.8 GB 2.5 GB
Fits Get file →
Q8_03.2 GB 3.9 GB
Fits Get file →
BF166.0 GB 6.7 GB
Fits Get file →

What GPU do you need for ibnsina-llm/ibnsina-3b-v21h?

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: the best quant that fits is Q4_K_M (1.8 GB file, about 3.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.4 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (6.0 GB file, about 7.2 GB in use).

Which ibnsina-llm/ibnsina-3b-v21h quant should you choose?

Q4_K_M is the usual starting point for ibnsina-llm/ibnsina-3b-v21h: it balances file size and quality well. Here it is a 1.8 GB file.

The Q8_0 file is 3.2 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters3B
Layers40
Trained context2,048 tokens
KV cache (fp16)80 KB per token

Source

Quantized byibnsina-llm
FamilyIbnsina
Licenseapache-2.0
Downloads (HF)116
Last updated2026-09-10

Frequently asked questions about ibnsina-llm/ibnsina-3b-v21h

How much VRAM does ibnsina-llm/ibnsina-3b-v21h need?

About 3.0 GB at Q4_K_M with an 8K context window. That is the 1.8 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 ibnsina-llm/ibnsina-3b-v21h on an 8 GB GPU?

Yes, with BF16: the 6.0 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 ibnsina-llm/ibnsina-3b-v21h GGUF?

It depends on the quant: Q4_K_M is 1.8 GB, Q8_0 is 3.2 GB, BF16 is 6.0 GB.

What context length does ibnsina-llm/ibnsina-3b-v21h support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.7 GB at 8K and 0.2 GB at 2K.

Where can I download ibnsina-llm/ibnsina-3b-v21h GGUF?

The files are on Hugging Face in the ibnsina-llm/ibnsina-3b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ibnsina-llm/ibnsina-3b-v21h 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.

Similar models

Browse all →

More from ibnsina-llm

All by ibnsina-llm →

More Ibnsina models

All Ibnsina →

Other tiny models

All tiny models →