Falcon-H1-1.5B-Instruct needs about 1.6 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 26 quants, from 0.4 GB (IQ1_S) to 3.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.8 GB.
Falcon-H1-1.5B-Instruct – 1.55 B parameter hybrid LLM in GGUF format
Falcon-H1-1.5B-Instruct is a 1.55 B parameter causal decoder-only model built on a hybrid Transformer‑Mamba architecture. It supports 131072‑token context and is available in multiple GGUF quantizations for llama.cpp.
Good at
- Instruction following
- Long‑context reasoning
- Multilingual text generation
Limits
- No vision support
- License is other
- Context limited to 131072 tokens
Best for
- Chatbots on modest GPUs
- Fine‑tuning for niche tasks
- Rapid prototyping with low memory
Who it’s for. Developers and researchers needing a lightweight Falcon variant for instruction‑based tasks. The model is suitable for environments where GPU memory is constrained but long‑context capability is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.4 GB | 1.1 GB | Fits | Get file → | |
| IQ1_M | 0.5 GB | 1.2 GB | Fits | Get file → | |
| IQ2_XXS | 0.5 GB | 1.2 GB | Fits | Get file → | |
| IQ2_M | 0.6 GB | 1.3 GB | Fits | Get file → | |
| Q2_K | 0.6 GB | 1.3 GB | Fits | Get file → | |
| Q2_K_L | 0.6 GB | 1.3 GB | Fits | Get file → | |
| IQ3_XXS | 0.7 GB | 1.4 GB | Fits | Get file → | |
| Q2_K_XL | 0.7 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.7 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_M | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_XL | 0.8 GB | 1.5 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 1.6 GB | Fits | Get file → | |
| IQ4_NL | 0.9 GB | 1.6 GB | Fits | Get file → | |
| Q4_0 | 0.9 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_S | 0.9 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.9 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_XL | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q4_1 | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_S | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_M | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_XL | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q6_K | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q6_K_XL | 1.4 GB | 2.1 GB | Fits | Get file → | |
| Q8_0 | 1.7 GB | 2.4 GB | Fits | Get file → | |
| Q8_K_XL | 2.1 GB | 2.8 GB | Fits | Get file → | |
| BF16 | 3.1 GB | 3.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (file size 0.92 GB, memory 1.6 GB at 8k context). If 12 GB VRAM is available, Q4_K_XL (0.96 GB, 1.7 GB) or Q5_K_S (1.09 GB, 1.8 GB) provide higher quality. For 16 GB VRAM, Q6_K (1.28 GB, 2 GB) or Q6_K_XL (1.41 GB, 2.1 GB) are recommended.
What GPU do you need for Falcon-H1-1.5B-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 BF16 (3.1 GB file, about 3.8 GB in use).
Which Falcon-H1-1.5B-Instruct quant should you choose?
Q4_K_M is the usual starting point for Falcon-H1-1.5B-Instruct: it balances file size and quality well. Here it is a 0.9 GB file.
The Q8_0 file is 1.7 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 0.4 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-H1-1.5B-Instruct
How much VRAM does Falcon-H1-1.5B-Instruct need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.9 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-H1-1.5B-Instruct on an 8 GB GPU?
Yes, with BF16: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Falcon-H1-1.5B-Instruct GGUF?
It depends on the quant: IQ1_S is 0.4 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_M is 0.6 GB, Q2_K is 0.6 GB, Q2_K_L is 0.6 GB and 20 more.
What context length does Falcon-H1-1.5B-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 0.2 GB at 8K and 0.8 GB at 32K.
Where can I download Falcon-H1-1.5B-Instruct GGUF?
The files are on Hugging Face in the unsloth/Falcon-H1-1.5B-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-H1-1.5B-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-H1-1.5B-Instruct on 8 GB VRAM?
Yes, using Q4_0 or Q4_K_S which require about 1.6 GB of VRAM at 8k context.
Does this model support image input?
No, the model has no vision capabilities.
What is the maximum context length?
The model supports up to 131072 tokens.