Olmo 3 7B Instruct Heretic needs about 9.0 GB of memory at IQ4_NL (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 13 quants, from 3.1 GB (IQ3_XS) to 14.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.
Olmo 3 7B Instruct Heretic is a 7.3B-parameter OLMo model in GGUF format, quantized by ChiKoi7. Its trained context length is 64K tokens. The repository has 13 quant files, from 3.1 GB (IQ3_XS) to 14.6 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XS | 3.1 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_S | 3.3 GB | 8.1 GB | Too big | Get file → | |
| IQ3_M | 3.5 GB | 8.3 GB | Too big | Get file → | |
| Q3_K_M | 3.7 GB | 8.4 GB | Too big | Get file → | |
| Q3_K_L | 4.0 GB | 8.7 GB | Too big | Get file → | |
| IQ4_XS | 4.0 GB | 8.8 GB | Too big | Get file → | |
| IQ4_NL | 4.2 GB | 9.0 GB | Too big | Get file → | |
| Q4_K_S | 4.2 GB | 9.0 GB | Too big | Get file → | |
| Q5_K_S | 5.1 GB | 9.9 GB | Too big | Get file → | |
| Q5_K_M | 5.2 GB | 10.0 GB | Too big | Get file → | |
| Q6_K | 6.0 GB | 10.8 GB | Too big | Get file → | |
| Q8_0 | 7.8 GB | 12.6 GB | Too big | Get file → | |
| F16 | 14.6 GB | 19.4 GB | Too big | Get file → |
What GPU do you need for Olmo 3 7B Instruct Heretic?
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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is IQ3_XS (3.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 10.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (7.8 GB file, about 12.6 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (14.6 GB file, about 19.4 GB in use).
Which Olmo 3 7B Instruct Heretic quant should you choose?
IQ4_NL (4.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ3_XS at 3.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Olmo 3 7B Instruct Heretic
How much VRAM does Olmo 3 7B Instruct Heretic need?
About 9.0 GB at IQ4_NL with an 8K context window. That is the 4.2 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 Olmo 3 7B Instruct Heretic on an 8 GB GPU?
Yes, with IQ3_XS: the 3.1 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 Olmo 3 7B Instruct Heretic GGUF?
It depends on the quant: IQ3_XS is 3.1 GB, Q3_K_S is 3.3 GB, IQ3_M is 3.5 GB, Q3_K_M is 3.7 GB, Q3_K_L is 4.0 GB, IQ4_XS is 4.0 GB and 7 more.
What context length does Olmo 3 7B Instruct Heretic support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.
Where can I download Olmo 3 7B Instruct Heretic GGUF?
The files are on Hugging Face in the ChiKoi7/Olmo-3-7B-Instruct-Heretic-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 Olmo 3 7B Instruct Heretic 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.