Falcon3 3B Base needs about 3.2 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.9 GB (IQ1_S) to 2.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.0 GB.
Falcon3 3B Base – 3.23B parameter instruction LLM with 8K context
Falcon3 3B Base is a 3.23B parameter transformer model trained on 100 GT of multilingual data. It supports English, French, Spanish, and Portuguese and offers strong reasoning, language understanding, and code performance. The model is available in multiple GGUF quantizations for efficient deployment.
Good at
- Reasoning and language understanding
- Instruction following
- Code and mathematics tasks
Limits
- No vision support
- Requires finetuning for most use cases
- License is TII Falcon-LLM License 2.0
Best for
- Chatbots with 8K context
- Small‑scale research prototypes
- Embedded inference on GPUs with 8–12 GB VRAM
Who it’s for. Developers and researchers needing a lightweight Falcon model for instruction following and reasoning tasks. The model is suitable for environments where GPU memory is limited and fine‑tuning is planned.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.9 GB | 2.2 GB | Fits | Get file → | |
| IQ1_M | 1.0 GB | 2.2 GB | Fits | Get file → | |
| IQ2_XXS | 1.0 GB | 2.3 GB | Fits | Get file → | |
| IQ2_XS | 1.1 GB | 2.4 GB | Fits | Get file → | |
| IQ2_S | 1.2 GB | 2.4 GB | Fits | Get file → | |
| IQ2_M | 1.3 GB | 2.5 GB | Fits | Get file → | |
| Q2_K_S | 1.3 GB | 2.5 GB | Fits | Get file → | |
| Q2_K | 1.4 GB | 2.6 GB | Fits | Get file → | |
| IQ3_XXS | 1.4 GB | 2.6 GB | Fits | Get file → | |
| IQ3_XS | 1.5 GB | 2.7 GB | Fits | Get file → | |
| IQ3_S | 1.5 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.8 GB | Fits | Get file → | |
| IQ3_M | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_M | 1.7 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_L | 1.8 GB | 3.0 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 3.1 GB | Fits | Get file → | |
| Q4_0 | 1.9 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_S | 1.9 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 3.2 GB | Fits | Get file → | |
| 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 → |
For 8 GB VRAM, use IQ1_S (0.92 GB file, 2.2 GB memory at 8K context) or IQ1_M (0.97 GB file). For 12 GB VRAM, Q4_K_M (2.01 GB file, 3.2 GB memory) offers a good balance of size and performance. Higher quants such as Q5_K_M or Q6_K provide better quality at the cost of more memory.
What GPU do you need for 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).
Which Falcon3 3B Base quant should you choose?
Q4_K_M is the usual starting point for Falcon3 3B Base: it balances file size and quality well. Here it is a 2.0 GB file.
If memory is tight, the smallest file is IQ1_S at 0.9 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
Source
Frequently asked questions about Falcon3 3B Base
How much VRAM does Falcon3 3B Base need?
About 3.2 GB at Q4_K_M with an 8K context window. That is the 2.0 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 Falcon3 3B Base on an 8 GB GPU?
Yes, with Q6_K: the 2.7 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Falcon3 3B Base GGUF?
It depends on the quant: IQ1_S is 0.9 GB, IQ1_M is 1.0 GB, IQ2_XXS is 1.0 GB, IQ2_XS is 1.1 GB, IQ2_S is 1.2 GB, IQ2_M is 1.3 GB and 16 more.
What context length does 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 Falcon3 3B Base GGUF?
The files are on Hugging Face in the mradermacher/Falcon3-3B-Base-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 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 a GPU with 8 GB VRAM?
Yes, the IQ1_S or IQ1_M quantizations require about 2.2 GB of VRAM at 8K context, leaving headroom for batch processing.
Which languages does Falcon3 3B Base support?
The model supports English, French, Spanish, and Portuguese.
What license applies to Falcon3 3B Base?
The model is released under the TII Falcon-LLM License 2.0.