rwkv7-g1k-1.5b-20260930-ctx25600.pth needs about 1.6 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.0 GB (Q4_K_M) to 3.1 GB.
RWKV7-G1k 1.5B base model for local inference
RWKV7-G1k 1.5B is a 1.53 billion‑parameter recurrent language model. It is available in GGUF format for use with llama.cpp and Ollama. The model is trained on a large context of 1,048,576 tokens and supports reasoning tasks.
Good at
- Reasoning
- Large context handling
- Recurrent architecture
Limits
- No vision support
- Not instruction‑tuned
- Requires 8 k context for memory estimates
Best for
- Local text generation
- Fine‑tuning on custom data
- Research on recurrent models
Who it’s for. Developers and researchers who need a lightweight, local language model for reasoning tasks. The model is suitable for fine‑tuning and experimentation on systems with limited GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 1.2 GB | 1.8 GB | Fits | Get file → | |
| Q6_K | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q8_0 | 1.7 GB | 2.4 GB | Fits | Get file → | |
| — | 3.1 GB | 3.9 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (1.02 GB, 1.6 GB memory) or Q5_K_M (1.18 GB, 1.8 GB memory) are recommended. If more precision is needed and memory allows, Q6_K (1.34 GB, 2 GB memory) can be used. Larger quants exceed typical consumer GPU budgets.
What GPU do you need for rwkv7-g1k-1.5b-20260930-ctx25600.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 the main file (3.1 GB file, about 3.9 GB in use).
Which rwkv7-g1k-1.5b-20260930-ctx25600.pth quant should you choose?
Q4_K_M is the usual starting point for rwkv7-g1k-1.5b-20260930-ctx25600.pth: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about rwkv7-g1k-1.5b-20260930-ctx25600.pth
How much VRAM does rwkv7-g1k-1.5b-20260930-ctx25600.pth need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 1.0 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-g1k-1.5b-20260930-ctx25600.pth on an 8 GB GPU?
Yes, with the smaller files: the 3.1 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of rwkv7-g1k-1.5b-20260930-ctx25600.pth GGUF?
It depends on the quant: Q4_K_M is 1.0 GB, Q5_K_M is 1.2 GB, Q6_K is 1.3 GB, Q8_0 is 1.7 GB, file is 3.1 GB.
What context length does rwkv7-g1k-1.5b-20260930-ctx25600.pth support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download rwkv7-g1k-1.5b-20260930-ctx25600.pth GGUF?
The files are on Hugging Face in the shoumenchougou/RWKV7-G1k-1.5B-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-g1k-1.5b-20260930-ctx25600.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, Q4_K_M or Q5_K_M can run on 8 GB VRAM with about 1.6–1.8 GB memory usage at 8 k context.
Is this model instruction‑tuned?
No, it is a base language model and may not follow instructions consistently.
What is the context length supported?
The model was trained with 1,048,576 tokens and supports up to 8 k context for inference.