Falcon-H1-3B-Instruct needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 26 quants, from 0.8 GB (IQ1_S) to 6.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.
Falcon-H1-3B-Instruct, a 3.15B parameter instruction‑tuned model
Falcon-H1-3B-Instruct is a causal decoder‑only model based on the Falcon‑H1 architecture. It supports English and multilingual text generation and is released under the Falcon‑LLM License.
Good at
- Instruction following
- Reasoning tasks
- Multilingual text generation
Limits
- No vision support
- Requires 8k context for memory estimates
- License not open source
Best for
- Chatbots with limited GPU memory
- Rapid prototyping of instruction models
- Educational demonstrations
Who it’s for. Developers and researchers who need a compact Falcon model for instruction‑based tasks. The model is suitable for environments where GPU memory is constrained but high‑quality text generation is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.8 GB | 1.6 GB | Fits | Get file → | |
| IQ1_M | 0.9 GB | 1.6 GB | Fits | Get file → | |
| IQ2_XXS | 0.9 GB | 1.7 GB | Fits | Get file → | |
| IQ2_M | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q2_K | 1.2 GB | 2.0 GB | Fits | Get file → | |
| Q2_K_L | 1.2 GB | 2.0 GB | Fits | Get file → | |
| Q2_K_XL | 1.3 GB | 2.0 GB | Fits | Get file → | |
| IQ3_XXS | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 1.4 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_M | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_XL | 1.6 GB | 2.3 GB | Fits | Get file → | |
| IQ4_XS | 1.7 GB | 2.5 GB | Fits | Get file → | |
| IQ4_NL | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_0 | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_XL | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q4_1 | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_XL | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q6_K_XL | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 4.1 GB | Fits | Get file → | |
| Q8_K_XL | 3.9 GB | 4.7 GB | Fits | Get file → | |
| BF16 | 6.3 GB | 7.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K or Q4_K_M (est. 2.6 GB memory). For 16 GB VRAM, Q5_K_S or Q5_K_M (est. 3 GB). For 24 GB VRAM, Q6_K or Q6_K_XL (est. 3.4–3.6 GB).
What GPU do you need for Falcon-H1-3B-Instruct?
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_XL (2.8 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_K_XL (3.9 GB file, about 4.7 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (6.3 GB file, about 7.1 GB in use).
Which Falcon-H1-3B-Instruct quant should you choose?
Q4_K_M is the usual starting point for Falcon-H1-3B-Instruct: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.4 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.
If memory is tight, the smallest file is IQ1_S at 0.8 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-H1-3B-Instruct
How much VRAM does Falcon-H1-3B-Instruct need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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-H1-3B-Instruct on an 8 GB GPU?
Yes, with BF16: the 6.3 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Falcon-H1-3B-Instruct GGUF?
It depends on the quant: IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 0.9 GB, IQ2_M is 1.1 GB, Q2_K is 1.2 GB, Q2_K_L is 1.2 GB and 20 more.
What context length does Falcon-H1-3B-Instruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.
Where can I download Falcon-H1-3B-Instruct GGUF?
The files are on Hugging Face in the unsloth/Falcon-H1-3B-Instruct-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-H1-3B-Instruct 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 Falcon-H1-3B-Instruct on 8 GB VRAM?
Yes, using Q4_K or Q4_K_M quantizations which estimate 2.6 GB memory at 8k context.
Does the model support image input?
No, Falcon-H1-3B-Instruct is a text‑only model.
What license applies to this model?
The model is released under the Falcon‑LLM License, not an open source license.