rwkv7 g1h 13.3b i1 needs about 10.7 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 0.0 GB to 11.6 GB (Q6_K).
rwkv7 g1h 13.3b i1 is a 13.3B-parameter Rwkv model in GGUF format, quantized by RemySkye. Its trained context length is 1024K tokens. The repository has 24 quant files, from 0.0 GB to 11.6 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ1_S | 3.8 GB | 4.7 GB | Fits | Get file → | |
| IQ1_M | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ2_XXS | 4.5 GB | 5.6 GB | Fits | Get file → | |
| IQ2_XS | 4.9 GB | 6.0 GB | Fits | Get file → | |
| IQ2_S | 5.0 GB | 6.1 GB | Fits | Get file → | |
| IQ2_M | 5.3 GB | 6.5 GB | Fits | Get file → | |
| Q2_K | 5.4 GB | 6.6 GB | Fits | Get file → | |
| IQ3_XXS | 6.1 GB | 7.3 GB | Tight | Get file → | |
| IQ3_S | 6.7 GB | 8.0 GB | Too big | Get file → | |
| Q3_K_S | 6.7 GB | 8.0 GB | Too big | Get file → | |
| Q3_K_M | 7.7 GB | 9.1 GB | Too big | Get file → | |
| IQ4_XS | 8.0 GB | 9.5 GB | Too big | Get file → | |
| IQ4_NL | 8.4 GB | 9.9 GB | Too big | Get file → | |
| Q4_0 | 8.4 GB | 9.9 GB | Too big | Get file → | |
| Q4_K_S | 8.4 GB | 9.9 GB | Too big | Get file → | |
| Q3_K_L | 8.4 GB | 9.9 GB | Too big | Get file → | |
| Q4_K_M | 9.1 GB | 10.7 GB | Too big | Get file → | |
| Q4_1 | 9.2 GB | 10.8 GB | Too big | Get file → | |
| Q5_0 | 10.0 GB | 11.7 GB | Too big | Get file → | |
| Q5_K_S | 10.0 GB | 11.7 GB | Too big | Get file → | |
| Q5_K_M | 10.3 GB | 12.1 GB | Too big | Get file → | |
| Q5_1 | 10.7 GB | 12.5 GB | Too big | Get file → | |
| Q6_K | 11.6 GB | 13.5 GB | Too big | Get file → |
What GPU do you need for rwkv7 g1h 13.3b i1?
These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is IQ2_XS (4.9 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_S (6.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_0 (10.0 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (11.6 GB file, about 13.5 GB in use).
Which rwkv7 g1h 13.3b i1 quant should you choose?
Q4_K_M is the usual starting point for rwkv7 g1h 13.3b i1: it balances file size and quality well. Here it is a 9.1 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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 rwkv7 g1h 13.3b i1
How much VRAM does rwkv7 g1h 13.3b i1 need?
About 10.7 GB at Q4_K_M with an 8K context window. That is the 9.1 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 rwkv7 g1h 13.3b i1 on an 8 GB GPU?
Yes, with IQ3_S: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of rwkv7 g1h 13.3b i1 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.8 GB, IQ1_M is 4.1 GB, IQ2_XXS is 4.5 GB, IQ2_XS is 4.9 GB, IQ2_S is 5.0 GB and 18 more.
What context length does rwkv7 g1h 13.3b i1 support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download rwkv7 g1h 13.3b i1 GGUF?
The files are on Hugging Face in the RemySkye/rwkv7-g1h-13.3b-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 rwkv7 g1h 13.3b i1 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.