RW

RWKV6 3B Chn UnlimitedRP Mini Chat HF

RwkvGGUF by mzwingUpdated 2025-02-01
Download on Hugging Face
Parameters3.1B
Context1024K
Layers32
Architecturerwkv6
Smallest quant0.9 GB
Quick answer

RWKV6 3B Chn UnlimitedRP Mini Chat 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 30 quants, from 0.9 GB (IQ1_S) to 6.3 GB (F16).

RWKV6 3B Chn UnlimitedRP Mini Chat HF – 3.1B Chinese chat model

RWKV6 3B Chn UnlimitedRP Mini Chat HF is a 3.1B parameter model trained on 1,048,576 token context. It is released under apache-2.0 and supports Chinese language chat. The model is available in multiple GGUF quantizations.

Good at

  • Chinese chat
  • Long‑context conversation
  • Low‑memory inference

Limits

  • No vision support
  • Requires 1,000,000+ token context
  • License is apache-2.0

Best for

  • Chatbots needing long context
  • Local Chinese language assistants
  • Research on 3B parameter models

Who it’s for. Developers building local Chinese chat applications or researchers needing a 3B parameter model with extended context. The model is suitable for environments where 8‑k token context is sufficient and memory resources are moderate.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.9 GB 1.5 GB
Fits Get file →
IQ1_M0.9 GB 1.5 GB
Fits Get file →
TQ1_01.0 GB 1.6 GB
Fits Get file →
IQ2_XXS1.0 GB 1.6 GB
Fits Get file →
TQ2_01.1 GB 1.7 GB
Fits Get file →
IQ2_XS1.1 GB 1.7 GB
Fits Get file →
IQ2_S1.1 GB 1.8 GB
Fits Get file →
IQ2_M1.2 GB 1.9 GB
Fits Get file →
Q2_K1.2 GB 1.9 GB
Fits Get file →
Q2_K_S1.2 GB 1.9 GB
Fits Get file →
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_L1.5 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 →
IQ4_NL1.9 GB 2.6 GB
Fits Get file →
Q4_01.9 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_12.1 GB 2.9 GB
Fits Get file →
Q5_02.3 GB 3.1 GB
Fits Get file →
Q5_K_M2.3 GB 3.1 GB
Fits Get file →
Q5_K_S2.3 GB 3.1 GB
Fits Get file →
Q5_12.5 GB 3.3 GB
Fits Get file →
Q6_K2.7 GB 3.5 GB
Fits Get file →
Q8_03.4 GB 4.3 GB
Fits Get file →
F166.3 GB 7.5 GB
Tight Get file →

For 8‑GB VRAM, use IQ1_S or IQ1_M (file size 0.86–0.92 GB, memory 1.5 GB). For 12‑GB VRAM, IQ4_K_M or Q4_K_M (1.92 GB, 2.6 GB). For 16‑GB VRAM, Q5_0 or Q5_K_M (2.28 GB, 3.1 GB). Memory estimates are approximate.

What GPU do you need for RWKV6 3B Chn UnlimitedRP Mini Chat 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 Q6_K (2.7 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.3 GB file, about 7.5 GB in use).

Which RWKV6 3B Chn UnlimitedRP Mini Chat HF quant should you choose?

Q4_K_M is the usual starting point for RWKV6 3B Chn UnlimitedRP Mini Chat HF: it balances file size and quality well. Here it is a 1.9 GB file.

The Q8_0 file is 3.4 GB, about 1.8 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 IQ1_S at 0.9 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

Architecturerwkv6
Parameters3.1B
Layers32
Trained context1,048,576 tokens

Source

Quantized bymzwing
FamilyRwkv
Licenseapache-2.0
Downloads (HF)801
Last updated2025-02-01

Frequently asked questions about RWKV6 3B Chn UnlimitedRP Mini Chat HF

How much VRAM does RWKV6 3B Chn UnlimitedRP Mini Chat 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 RWKV6 3B Chn UnlimitedRP Mini Chat HF on an 8 GB GPU?

Yes, with F16: the 6.3 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of RWKV6 3B Chn UnlimitedRP Mini Chat HF GGUF?

It depends on the quant: IQ1_S is 0.9 GB, IQ1_M is 0.9 GB, TQ1_0 is 1.0 GB, IQ2_XXS is 1.0 GB, TQ2_0 is 1.1 GB, IQ2_XS is 1.1 GB and 24 more.

What context length does RWKV6 3B Chn UnlimitedRP Mini Chat HF support?

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

Where can I download RWKV6 3B Chn UnlimitedRP Mini Chat HF GGUF?

The files are on Hugging Face in the mzwing/RWKV6-3B-Chn-UnlimitedRP-mini-chat-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 RWKV6 3B Chn UnlimitedRP Mini Chat 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, the IQ1_S and IQ1_M quantizations use about 1.5 GB of VRAM at 8k context.

Does this model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mzwing

All by mzwing →

More Rwkv models

All Rwkv →

Other tiny models

All tiny models →