rwkv7-2.9B-world needs about 2.6 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 27 quants, from 1.0 GB (TQ1_0) to 5.9 GB (BF16).
rwkv7-2.9B-world is a 2.95B-parameter Rwkv model in GGUF format, quantized by Mungert. Its trained context length is 1024K tokens. The repository has 27 quant files, from 1.0 GB (TQ1_0) to 5.9 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 1.0 GB | 1.6 GB | Fits | Get file → | |
| TQ2_0 | 1.1 GB | 1.7 GB | Fits | Get file → | |
| IQ3_XXS | 1.4 GB | 2.0 GB | Fits | Get file → | |
| IQ3_M | 1.5 GB | 2.2 GB | Fits | Get file → | |
| IQ3_S | 1.5 GB | 2.2 GB | Fits | Get file → | |
| IQ3_XS | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_M | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.2 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 2.5 GB | Fits | Get file → | |
| Q4_0 | 1.8 GB | 2.6 GB | Fits | Get file → | |
| IQ4_NL | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_S | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q4_1 | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q5_0 | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.0 GB | Fits | Get file → | |
| BF16 | 2.3 GB | 3.1 GB | Fits | Get file → | |
| F16 | 2.3 GB | 3.1 GB | Fits | Get file → | |
| Q5_1 | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q6_K_M | 2.6 GB | 3.4 GB | Fits | Get file → | |
| BF16 | 3.0 GB | 3.8 GB | Fits | Get file → | |
| F16 | 3.0 GB | 3.8 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.1 GB | Fits | Get file → | |
| BF16 | 3.6 GB | 4.5 GB | Fits | Get file → | |
| F16 | 3.6 GB | 4.5 GB | Fits | Get file → | |
| BF16 | 5.9 GB | 7.1 GB | Fits | Get file → |
What GPU do you need for rwkv7-2.9B-world?
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 BF16 (3.0 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.6 GB file, about 4.5 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.9 GB file, about 7.1 GB in use).
Which rwkv7-2.9B-world quant should you choose?
Q4_K_M is the usual starting point for rwkv7-2.9B-world: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.3 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 TQ1_0 at 1.0 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 rwkv7-2.9B-world
How much VRAM does rwkv7-2.9B-world need?
About 2.6 GB at Q4_K_M with an 8K context window. That is the 1.9 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 rwkv7-2.9B-world on an 8 GB GPU?
Yes, with BF16: the 5.9 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of rwkv7-2.9B-world GGUF?
It depends on the quant: TQ1_0 is 1.0 GB, TQ2_0 is 1.1 GB, IQ3_XXS is 1.4 GB, IQ3_M is 1.5 GB, IQ3_S is 1.5 GB, IQ3_XS is 1.5 GB and 21 more.
What context length does rwkv7-2.9B-world support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download rwkv7-2.9B-world GGUF?
The files are on Hugging Face in the Mungert/rwkv7-2.9B-world-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 rwkv7-2.9B-world 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.