rwkv7-g1h-2.9b-20260710-ctx10240.pth needs about 2.8 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 16 quants, from 1.2 GB (Q2_K) to 5.9 GB (BF16).
RWKV7‑G1H 2.9B reasoning model with 10k context
RWKV7‑G1H 2.9B is a pure RNN model trained on web, code, synthetic, instruction, chat and reasoning data. It supports up to 10,240 token context and is released under Apache‑2.0. The model is available in multiple GGUF quantizations.
Good at
- Reasoning tasks
- Instruction following
- Chat‑style dialogue
Limits
- No vision support
- Requires 8,000+ token context for full capability
- License is Apache‑2.0
Best for
- Fine‑tuning on custom instruction data
- Local inference on mobile devices
- Low‑latency chat applications
Who it’s for. Developers and researchers who need a lightweight, RNN‑based language model for reasoning and instruction tasks. The model is suitable for local inference on devices with limited VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.2 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_M | 1.8 GB | 2.5 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 2.5 GB | Fits | Get file → | |
| Q4_0 | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_S | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q3_K_L | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q4_1 | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 2.8 GB | Fits | Get file → | |
| Q5_0 | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.3 GB | 3.1 GB | Fits | Get file → | |
| Q5_1 | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q6_K | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.1 GB | Fits | Get file → | |
| BF16 | 5.9 GB | 7.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K_S (est. 2.6 GB at 8k context). For 4 GB VRAM, use Q3_K_S or Q3_K_M (est. 2.2–2.5 GB). For 2 GB VRAM, use Q2_K (est. 1.9 GB).
What GPU do you need for rwkv7-g1h-2.9b-20260710-ctx10240.pth?
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 Q6_K (2.6 GB file, about 3.4 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 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-g1h-2.9b-20260710-ctx10240.pth quant should you choose?
Q4_K_M is the usual starting point for rwkv7-g1h-2.9b-20260710-ctx10240.pth: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.3 GB, about 1.6 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 Q2_K at 1.2 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 rwkv7-g1h-2.9b-20260710-ctx10240.pth
How much VRAM does rwkv7-g1h-2.9b-20260710-ctx10240.pth need?
About 2.8 GB at Q4_K_M with an 8K context window. That is the 2.1 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-2.9b-20260710-ctx10240.pth 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-g1h-2.9b-20260710-ctx10240.pth GGUF?
It depends on the quant: Q2_K is 1.2 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.8 GB, IQ4_XS is 1.8 GB, Q4_0 is 1.9 GB, Q4_K_S is 1.9 GB and 10 more.
What context length does rwkv7-g1h-2.9b-20260710-ctx10240.pth support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download rwkv7-g1h-2.9b-20260710-ctx10240.pth GGUF?
The files are on Hugging Face in the RemySkye/rwkv7-g1h-2.9b-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-2.9b-20260710-ctx10240.pth 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 this model on 8 GB VRAM?
Yes, the Q4_0 and Q4_K_S quantizations use about 2.6 GB at 8k context, fitting within 8 GB VRAM with headroom.
Does the model support vision?
No, the model has no vision capabilities.
What is the context length I can use?
The model supports up to 10,240 tokens, but the provided quantizations are estimated at 8k context.