Salience 1.5 Flash needs about 20.0 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.1 GB to 61.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Salience 1.5 Flash – a 30B Mixture‑of‑Experts vision‑language model
Salience 1.5 Flash is a 30B‑parameter sparse model that activates only 3.3B parameters per token. It supports coding, reasoning, tools, and vision, with a context window up to 1M tokens. The model is released under Apache‑2.0 and available in multiple GGUF quantizations.
Good at
- Coding and debugging real code
- Agentic tool calls
- Multimodal vision and video understanding
Limits
- No chat‑pleasantry focus
- Requires large VRAM for full precision
- No native vision support without GGUF
Best for
- Developing production‑grade interfaces
- Designing UI components
- Running long‑context reasoning tasks
Who it’s for. Engineers and designers who need a fast, multimodal model for practical coding, agentic execution, and design tasks. The model is suited for users who prefer function over chat style responses.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.4 GB | Fits | Get file → | |
| IQ2_XXS | 8.4 GB | 9.7 GB | Too big | Get file → | |
| IQ2_XS | 9.3 GB | 10.6 GB | Too big | Get file → | |
| IQ2_S | 9.6 GB | 10.9 GB | Too big | Get file → | |
| IQ2_M | 10.5 GB | 11.8 GB | Too big | Get file → | |
| Q2_K | 11.0 GB | 12.3 GB | Too big | Get file → | |
| Q2_K_L | 11.3 GB | 12.6 GB | Too big | Get file → | |
| IQ3_XXS | 12.9 GB | 14.3 GB | Too big | Get file → | |
| Q3_K_S | 13.5 GB | 14.8 GB | Too big | Get file → | |
| IQ3_XS | 14.1 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_M | 14.1 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_L | 14.7 GB | 16.0 GB | Too big | Get file → | |
| IQ3_M | 14.8 GB | 16.1 GB | Too big | Get file → | |
| Q3_K_XL | 15.0 GB | 16.3 GB | Too big | Get file → | |
| IQ4_XS | 16.5 GB | 17.8 GB | Too big | Get file → | |
| IQ4_NL | 17.5 GB | 18.8 GB | Too big | Get file → | |
| Q4_0 | 17.5 GB | 18.8 GB | Too big | Get file → | |
| Q4_K_S | 18.0 GB | 19.3 GB | Too big | Get file → | |
| Q4_K_M | 18.7 GB | 20.0 GB | Too big | Get file → | |
| Q4_K_L | 18.9 GB | 20.2 GB | Too big | Get file → | |
| Q4_1 | 19.3 GB | 20.6 GB | Too big | Get file → | |
| Q5_K_S | 21.1 GB | 22.5 GB | Too big | Get file → | |
| Q5_K_M | 21.8 GB | 23.1 GB | Too big | Get file → | |
| Q5_K_L | 22.0 GB | 23.3 GB | Too big | Get file → | |
| Q6_K | 26.4 GB | 27.7 GB | Too big | Get file → | |
| Q6_K_L | 26.6 GB | 27.9 GB | Too big | Get file → | |
| Q8_0 | 32.5 GB | 33.8 GB | Too big | Get file → | |
| BF16 | 61.1 GB (2 parts) | 62.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (file size 8.43 GB, memory 9.7 GB at 8k context). For 16 GB VRAM, IQ4_0 (file size 17.48 GB, memory 18.8 GB) offers a good balance of quality and size. For 32 GB VRAM, Q8_0 (file size 32.48 GB, memory 33.8 GB) provides the highest fidelity.
What GPU do you need for Salience 1.5 Flash?
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 the main file (0.1 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_M (10.5 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_L (14.7 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_L (22.0 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_L (26.6 GB file, about 27.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (32.5 GB file, about 33.8 GB in use).
Which Salience 1.5 Flash quant should you choose?
Q4_K_M is the usual starting point for Salience 1.5 Flash: it balances file size and quality well. Here it is a 18.7 GB file.
The Q8_0 file is 32.5 GB, about 1.7 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 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 Salience 1.5 Flash
How much VRAM does Salience 1.5 Flash need?
About 20.0 GB at Q4_K_M with an 8K context window. That is the 18.7 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 1.5 Flash on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Salience 1.5 Flash GGUF?
It depends on the quant: file is 0.1 GB, IQ2_XXS is 8.4 GB, IQ2_XS is 9.3 GB, IQ2_S is 9.6 GB, IQ2_M is 10.5 GB, Q2_K is 11.0 GB and 22 more.
What context length does Salience 1.5 Flash support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download Salience 1.5 Flash GGUF?
The files are on Hugging Face in the bartowski/vectionlabs_Salience-1.5-Flash-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 Salience 1.5 Flash 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 Salience 1.5 Flash on 8 GB VRAM?
Use the IQ2_XXS quant, which requires approximately 9.7 GB of VRAM at 8k context.
Does the model support vision input?
Yes, it includes a native vision encoder for images and video as first‑class inputs.
What license does the model use?
The model is released under the Apache‑2.0 license.