Falcon 11B needs about 9.4 GB of memory at Q4_K_M (a 6.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.6 GB (IQ1_S) to 9.2 GB (Q6_K).
Falcon 11B – 11B‑parameter causal decoder‑only model in GGUF format
Falcon 11B is an 11B‑parameter causal decoder‑only model built by TII. It is available in multiple GGUF quantizations and can be run with llama.cpp. The model was trained on over 5,000B tokens of RefinedWeb and curated corpora.
Good at
- Large‑scale text generation
- Research foundation for fine‑tuning
- Supports multiple European languages
Limits
- No vision support
- Requires 8‑k context for full performance
- License unknown
Best for
- Fine‑tuning for summarization
- Chatbot prototypes
- Academic research on LLMs
Who it’s for. Users who need a large, open‑source language model for research or fine‑tuning. The model is suitable for developers who can handle the lack of a clear license and the need for additional safety measures.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.6 GB | 3.6 GB | Fits | Get file → | |
| IQ1_M | 2.8 GB | 3.8 GB | Fits | Get file → | |
| IQ2_XXS | 3.1 GB | 4.1 GB | Fits | Get file → | |
| IQ2_XS | 3.4 GB | 4.5 GB | Fits | Get file → | |
| IQ2_S | 3.7 GB | 4.7 GB | Fits | Get file → | |
| IQ2_M | 3.9 GB | 5.0 GB | Fits | Get file → | |
| Q2_K | 4.3 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XXS | 4.4 GB | 5.5 GB | Fits | Get file → | |
| IQ3_XS | 4.8 GB | 5.8 GB | Fits | Get file → | |
| IQ3_S | 4.9 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_S | 4.9 GB | 5.9 GB | Fits | Get file → | |
| IQ3_M | 5.2 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_M | 5.4 GB | 6.4 GB | Fits | Get file → | |
| Q3_K_L | 5.8 GB | 6.8 GB | Fits | Get file → | |
| IQ4_XS | 6.0 GB | 7.0 GB | Fits | Get file → | |
| Q4_0 | 6.4 GB | 7.4 GB | Tight | Get file → | |
| Q4_0 | 6.4 GB | 7.4 GB | Tight | Get file → | |
| Q4_0 | 6.4 GB | 7.4 GB | Tight | Get file → | |
| Q4_K_S | 6.4 GB | 7.4 GB | Tight | Get file → | |
| Q4_0 | 6.4 GB | 7.4 GB | Tight | Get file → | |
| Q4_K_M | 6.8 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_S | 7.7 GB | 8.7 GB | Too big | Get file → | |
| Q5_K_M | 8.2 GB | 9.2 GB | Too big | Get file → | |
| Q6_K | 9.2 GB | 10.2 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (2.56 GB, 5.1 GB VRAM) or IQ1_M (2.78 GB, 5.3 GB VRAM). For 12‑GB VRAM, IQ2_M (3.95 GB, 6.5 GB VRAM) or Q3_K_M (5.44 GB, 7.9 GB VRAM) are good choices. For 24‑GB VRAM, Q5_K_M (8.2 GB, 10.7 GB VRAM) or Q6_K (9.18 GB, 11.7 GB VRAM) provide higher quality.
What GPU do you need for Falcon 11B?
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: the best quant that fits is IQ2_XS (3.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_M (5.4 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.2 GB file, about 11.7 GB in use).
Which Falcon 11B quant should you choose?
Q4_K_M is the usual starting point for Falcon 11B: it balances file size and quality well. Here it is a 6.8 GB file.
If memory is tight, the smallest file is IQ1_S at 2.6 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 Falcon 11B
How much VRAM does Falcon 11B need?
About 9.4 GB at Q4_K_M with an 8K context window. That is the 6.8 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 Falcon 11B on an 8 GB GPU?
Yes, with Q3_K_M: the 5.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Falcon 11B GGUF?
It depends on the quant: IQ1_S is 2.6 GB, IQ1_M is 2.8 GB, IQ2_XXS is 3.1 GB, IQ2_XS is 3.4 GB, IQ2_S is 3.7 GB, IQ2_M is 3.9 GB and 18 more.
What context length does Falcon 11B support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.0 GB at 8K and 0.5 GB at 2K.
Where can I download Falcon 11B GGUF?
The files are on Hugging Face in the mradermacher/falcon-11B-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 Falcon 11B use?
Hugging Face lists the license as unknown. 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 Falcon 11B on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations which require about 5.1–5.3 GB VRAM at 8‑k context.
Does Falcon 11B support vision tasks?
No, Falcon 11B is a text‑only causal decoder‑only model.
What license applies to Falcon 11B?
The license is listed as unknown; users should verify usage rights before deployment.