Salience 1 9B Heretic needs about 6.3 GB of memory at IQ4_XS (a 4.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 19 quants, from 1.6 GB (Q1_0) to 16.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Salience 1 9B Heretic is a 8.19B-parameter Salience model in GGUF format, quantized by haffner. Its trained context length is 256K tokens. The repository has 19 quant files, from 1.6 GB (Q1_0) to 16.4 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q1_0 | 1.6 GB | 3.3 GB | Fits | Get file → | |
| TQ1_0 | 2.3 GB | 4.0 GB | Fits | Get file → | |
| TQ2_0 | 2.7 GB | 4.4 GB | Fits | Get file → | |
| Q2_K | 3.3 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.5 GB | Fits | Get file → | |
| IQ3_S | 3.8 GB | 5.5 GB | Fits | Get file → | |
| IQ3_M | 3.9 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_L | 4.4 GB | 6.1 GB | Fits | Get file → | |
| IQ4_XS | 4.6 GB | 6.3 GB | Fits | Get file → | |
| IQ4_NL | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_1 | 5.2 GB | 7.0 GB | Fits | Get file → | |
| Q5_0 | 5.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_S | 5.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 5.9 GB | 7.6 GB | Tight | Get file → | |
| Q5_1 | 6.2 GB | 7.9 GB | Tight | Get file → | |
| Q6_K | 6.7 GB | 8.4 GB | Too big | Get file → | |
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → | |
| BF16 | 16.4 GB | 18.1 GB | Too big | Get file → |
What GPU do you need for Salience 1 9B 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: the best quant that fits is TQ1_0 (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q3_K_M (4.1 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_1 (6.2 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.4 GB file, about 18.1 GB in use).
Which Salience 1 9B Heretic quant should you choose?
IQ4_XS (4.6 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 Q1_0 at 1.6 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Salience 1 9B Heretic
How much VRAM does Salience 1 9B Heretic need?
About 6.3 GB at IQ4_XS with an 8K context window. That is the 4.6 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 Salience 1 9B Heretic on an 8 GB GPU?
Yes, with Q5_1: the 6.2 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 Salience 1 9B Heretic GGUF?
It depends on the quant: Q1_0 is 1.6 GB, TQ1_0 is 2.3 GB, TQ2_0 is 2.7 GB, Q2_K is 3.3 GB, Q3_K_S is 3.8 GB, IQ3_S is 3.8 GB and 13 more.
What context length does Salience 1 9B Heretic support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Salience 1 9B Heretic GGUF?
The files are on Hugging Face in the haffner/Salience-1-9B-Heretic repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Salience 1 9B 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.