Granite 4.0 H Small Heretic_Lo needs about 25.3 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.1 GB to 26.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 21.5 GB.
Granite 4.0 H Small Heretic_Lo – 32B parameter long‑context instruct model
Granite 4.0 H Small Heretic_Lo is a 32.2B parameter model trained on 1,048,576 context tokens. It supports tool‑calling and is fine‑tuned for enterprise instruction following. The model is released under Apache 2.0 and supports multiple languages.
Good at
- Tool‑calling
- Long‑context instruction
- Enterprise chat
Limits
- No vision support
- Large VRAM requirement for higher quants
- License is Apache 2.0
Best for
- Building AI assistants
- Enterprise chatbots
- Code‑related tasks
Who it’s for. Developers and businesses needing a large‑context, instruction‑following model with tool‑calling. The model is suitable for multilingual applications and can be fine‑tuned for additional languages.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 6.0 GB | Fits | Get file → | |
| IQ1_S | 6.7 GB | 12.5 GB | Too big | Get file → | |
| IQ1_M | 7.4 GB | 13.2 GB | Too big | Get file → | |
| IQ2_XXS | 8.6 GB | 14.5 GB | Too big | Get file → | |
| IQ2_XS | 9.6 GB | 15.4 GB | Too big | Get file → | |
| IQ2_S | 9.6 GB | 15.5 GB | Too big | Get file → | |
| IQ2_M | 10.6 GB | 16.5 GB | Too big | Get file → | |
| Q2_K_S | 11.1 GB | 17.0 GB | Too big | Get file → | |
| Q2_K | 11.8 GB | 17.6 GB | Too big | Get file → | |
| IQ3_XXS | 12.5 GB | 18.4 GB | Too big | Get file → | |
| IQ3_XS | 13.4 GB | 19.3 GB | Too big | Get file → | |
| IQ3_S | 14.1 GB | 19.9 GB | Too big | Get file → | |
| Q3_K_S | 14.1 GB | 19.9 GB | Too big | Get file → | |
| IQ3_M | 14.2 GB | 20.1 GB | Too big | Get file → | |
| Q3_K_M | 15.4 GB | 21.2 GB | Too big | Get file → | |
| Q3_K_L | 16.5 GB | 22.3 GB | Too big | Get file → | |
| IQ4_XS | 17.3 GB | 23.1 GB | Too big | Get file → | |
| Q4_0 | 18.3 GB | 24.2 GB | Too big | Get file → | |
| Q4_K_S | 18.4 GB | 24.3 GB | Too big | Get file → | |
| Q4_K_M | 19.5 GB | 25.3 GB | Too big | Get file → | |
| Q4_1 | 20.3 GB | 26.1 GB | Too big | Get file → | |
| Q5_K_S | 22.2 GB | 28.1 GB | Too big | Get file → | |
| Q5_K_M | 22.9 GB | 28.7 GB | Too big | Get file → | |
| Q6_K | 26.5 GB | 32.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (6.65 GB file, 12.5 GB memory at 8 k context). For 12 GB VRAM, IQ1_M (7.38 GB file, 13.2 GB memory). For 16 GB VRAM, Q2_K (11.78 GB file, 17.6 GB memory).
What GPU do you need for Granite 4.0 H Small Heretic_Lo?
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 the main file (0.1 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 6.0 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_S (9.6 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (17.3 GB file, about 23.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (22.9 GB file, about 28.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (26.5 GB file, about 32.3 GB in use).
Which Granite 4.0 H Small Heretic_Lo quant should you choose?
Q4_K_M is the usual starting point for Granite 4.0 H Small Heretic_Lo: it balances file size and quality well. Here it is a 19.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Granite 4.0 H Small Heretic_Lo
How much VRAM does Granite 4.0 H Small Heretic_Lo need?
About 25.3 GB at Q4_K_M with an 8K context window. That is the 19.5 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 Granite 4.0 H Small Heretic_Lo on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite 4.0 H Small Heretic_Lo GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 6.7 GB, IQ1_M is 7.4 GB, IQ2_XXS is 8.6 GB, IQ2_XS is 9.6 GB, IQ2_S is 9.6 GB and 18 more.
What context length does Granite 4.0 H Small Heretic_Lo support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 5.4 GB at 8K and 21.5 GB at 32K.
Where can I download Granite 4.0 H Small Heretic_Lo GGUF?
The files are on Hugging Face in the mradermacher/granite-4.0-h-small-heretic_lo-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 Granite 4.0 H Small Heretic_Lo use?
Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?
Yes, the IQ1_S quant uses 6.65 GB file size and requires about 12.5 GB VRAM at 8 k context.
Does this model support vision?
No, the model does not include vision capabilities.
What license does this model use?
The model is released under the Apache 2.0 license.