GRaPE Flash needs about 5.8 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.6 GB (Q2_K) to 13.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
GRaPE Flash is a 6.92B-parameter OLMo model in GGUF format, quantized by SL-AI. Its trained context length is 32K tokens. The repository has 5 quant files, from 2.6 GB (Q2_K) to 13.8 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 4.2 GB | 5.8 GB | Fits | Get file → | |
| Q6_K | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q8_K | 7.4 GB | 8.9 GB | Too big | Get file → | |
| BF16 | 13.8 GB | 15.4 GB | Too big | Get file → |
What GPU do you need for GRaPE 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_M (4.2 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_K (7.4 GB file, about 8.9 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (13.8 GB file, about 15.4 GB in use).
Which GRaPE Flash quant should you choose?
Q4_K_M is the usual starting point for GRaPE Flash: it balances file size and quality well. Here it is a 4.2 GB file.
If memory is tight, the smallest file is Q2_K at 2.6 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 GRaPE Flash
How much VRAM does GRaPE Flash need?
About 5.8 GB at Q4_K_M 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 GRaPE Flash on an 8 GB GPU?
Yes, with Q6_K: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GRaPE Flash GGUF?
It depends on the quant: Q2_K is 2.6 GB, Q4_K_M is 4.2 GB, Q6_K is 5.7 GB, Q8_K is 7.4 GB, BF16 is 13.8 GB.
What context length does GRaPE Flash support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download GRaPE Flash GGUF?
The files are on Hugging Face in the SL-AI/GRaPE-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 GRaPE 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.