Models Tiiuae Falcon3 3B Base needs about 3.9 GB of memory at Q6_K (a 2.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 2.3 GB (Q5_K_S) to 6.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.0 GB.
Falcon3-3B-Base: 3.23B parameter LLaMA‑style model with 8K context
Falcon3-3B-Base is a 3.23B parameter transformer model based on the Falcon family. It supports English, French, Spanish, and Portuguese with a maximum context length of 8K tokens. The model is available in several GGUF quantizations for local deployment.
Good at
- Reasoning and language understanding
- Instruction following
- Code and mathematics tasks
Limits
- No vision support
- Requires fine‑tuning for most use cases
- License is TII Falcon‑LLM License 2.0
Best for
- Local inference on 8K context
- Fine‑tuning for specialized tasks
- Educational demonstrations
Who it’s for. Developers and researchers who need a lightweight Falcon model for local inference or fine‑tuning. The model is suitable for those who prefer open‑source LLMs with multilingual support and a moderate parameter count.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 2.3 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_M | 2.3 GB | 3.6 GB | Fits | Get file → | |
| Q6_K | 2.7 GB | 3.9 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 4.7 GB | Fits | Get file → | |
| — | 6.5 GB | 7.7 GB | Tight | Get file → |
For 8 GB VRAM, use Q5_K_S (2.28 GB file, 3.5 GB memory) or Q5_K_M (2.32 GB file, 3.6 GB memory). If 12 GB VRAM is available, Q6_K (2.65 GB file, 3.9 GB memory) is a good balance. The Q8_0 quant requires 3.44 GB file and 4.7 GB memory, suitable for higher precision needs.
What GPU do you need for Models Tiiuae Falcon3 3B Base?
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 Q6_K (2.7 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (6.5 GB file, about 7.7 GB in use).
Which Models Tiiuae Falcon3 3B Base quant should you choose?
Q6_K (2.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q5_K_S at 2.3 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Models Tiiuae Falcon3 3B Base
How much VRAM does Models Tiiuae Falcon3 3B Base need?
About 3.9 GB at Q6_K with an 8K context window. That is the 2.7 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 Models Tiiuae Falcon3 3B Base on an 8 GB GPU?
Yes, with the smaller files: the 6.5 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Models Tiiuae Falcon3 3B Base GGUF?
It depends on the quant: Q5_K_S is 2.3 GB, Q5_K_M is 2.3 GB, Q6_K is 2.7 GB, Q8_0 is 3.4 GB, file is 6.5 GB.
What context length does Models Tiiuae Falcon3 3B Base support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.7 GB at 8K and 3.0 GB at 32K.
Where can I download Models Tiiuae Falcon3 3B Base GGUF?
The files are on Hugging Face in the MaziyarPanahi/Falcon3-3B-Base-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 Models Tiiuae Falcon3 3B Base use?
Hugging Face lists the license as other. 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 Falcon3-3B-Base on 8 GB VRAM?
Yes, the Q5_K_S or Q5_K_M quantizations fit within 8 GB VRAM, using approximately 3.5–3.6 GB of memory at 8K context.
Does this model support vision tasks?
No, Falcon3-3B-Base is a text‑only model and does not include vision capabilities.
What is the maximum context length I can use?
The model supports up to 8K tokens of context length.