RW

RWKV7-Goose-World3-2.9B-HF

RwkvGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters2.95B
Context1024K
Layers32
Architecturerwkv7
Smallest quant1.4 GB
Quick answer

RWKV7-Goose-World3-2.9B-HF 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 25 quants, from 1.4 GB (IQ3_XXS) to 5.9 GB (BF16).

RWKV7-Goose-World3-2.9B-HF – 2.95B parameter RWKV model

RWKV7-Goose-World3-2.9B-HF is a 2.95B parameter language model based on RWKV-7 architecture. It was trained on 2T tokens from the World-v2.9 dataset, covering 100+ languages. The model is released under the apache-2.0 license.

Good at

  • Large context handling
  • Multilingual text generation
  • Fine‑tuning for specific domains

Limits

  • No vision support
  • Requires 8k context for estimates
  • Large memory for higher precision quantizations

Best for

  • Chatbots on modest GPUs
  • Local inference on CPUs with low VRAM
  • Fine‑tuning for niche language tasks

Who it’s for. Developers and researchers who need a large‑context RWKV model that can run locally. The model is suitable for those who have access to GPUs or CPUs that support 16‑bit or quantized inference and want a flexible, open‑source solution.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS1.4 GB 2.1 GB
Fits Get file →
IQ3_M1.5 GB 2.2 GB
Fits Get file →
IQ3_S1.5 GB 2.2 GB
Fits Get file →
IQ3_XS1.5 GB 2.2 GB
Fits Get file →
Q3_K_M1.5 GB 2.2 GB
Fits Get file →
Q3_K_S1.5 GB 2.2 GB
Fits Get file →
IQ4_XS1.8 GB 2.5 GB
Fits Get file →
Q4_01.8 GB 2.6 GB
Fits Get file →
IQ4_NL1.9 GB 2.6 GB
Fits Get file →
Q4_K_M1.9 GB 2.6 GB
Fits Get file →
Q4_K_S1.9 GB 2.6 GB
Fits Get file →
Q4_12.0 GB 2.8 GB
Fits Get file →
Q5_02.2 GB 3.0 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q5_K_S2.2 GB 3.0 GB
Fits Get file →
BF162.3 GB 3.1 GB
Fits Get file →
F162.3 GB 3.1 GB
Fits Get file →
Q5_12.4 GB 3.2 GB
Fits Get file →
Q6_K_M2.6 GB 3.4 GB
Fits Get file →
BF163.0 GB 3.8 GB
Fits Get file →
F163.0 GB 3.8 GB
Fits Get file →
Q8_03.3 GB 4.1 GB
Fits Get file →
BF163.6 GB 4.5 GB
Fits Get file →
F163.6 GB 4.5 GB
Fits Get file →
BF165.9 GB 7.1 GB
Fits Get file →

For 8 GB VRAM, use IQ4_XS (1.79 GB) or Q4_0 (1.83 GB). If 4 GB VRAM is available, IQ3_XXS (1.42 GB) or IQ3_M (1.54 GB) are suitable. For higher precision on 16 GB VRAM, Q5_0 (2.19 GB) or BF16 (2.31 GB) provide better accuracy while staying within memory limits.

What GPU do you need for RWKV7-Goose-World3-2.9B-HF?

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-Goose-World3-2.9B-HF quant should you choose?

Q4_K_M is the usual starting point for RWKV7-Goose-World3-2.9B-HF: 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 IQ3_XXS at 1.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturerwkv7
Parameters2.95B
Layers32
Trained context1,048,576 tokens

Source

Quantized byMungert
FamilyRwkv
Licenseapache-2.0
Downloads (HF)725
Last updated2025-09-24

Frequently asked questions about RWKV7-Goose-World3-2.9B-HF

How much VRAM does RWKV7-Goose-World3-2.9B-HF 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-Goose-World3-2.9B-HF 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-Goose-World3-2.9B-HF GGUF?

It depends on the quant: IQ3_XXS is 1.4 GB, IQ3_M is 1.5 GB, IQ3_S is 1.5 GB, IQ3_XS is 1.5 GB, Q3_K_M is 1.5 GB, Q3_K_S is 1.5 GB and 19 more.

What context length does RWKV7-Goose-World3-2.9B-HF support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download RWKV7-Goose-World3-2.9B-HF GGUF?

The files are on Hugging Face in the Mungert/RWKV7-Goose-World3-2.9B-HF-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-Goose-World3-2.9B-HF 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, quantizations such as IQ4_XS or Q4_0 fit within 8 GB VRAM and use about 2.5–2.6 GB of memory at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities and is purely text‑based.

What license applies to this model?

The model is released under the apache-2.0 license, allowing free use and modification.

Other GGUFs of rwkv-7-world

Similar models

Browse all →

More from Mungert

All by Mungert →

More Rwkv models

All Rwkv →

Other tiny models

All tiny models →