RW

rwkv 6 finch 1b6

RwkvGGUF by latestissueUpdated 2024-10-23
Download on Hugging Face
Parameters1.6B
Context1024K
Layers24
Architecturerwkv6
Smallest quant0.7 GB
Quick answer

rwkv 6 finch 1b6 needs about 1.6 GB of memory at Q4_K_S (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 23 quants, from 0.7 GB (Q2_K) to 6.4 GB (F32).

rwkv 6 finch 1b6 – 1.6 B parameter RWKV model

rwkv 6 finch 1b6 is a 1.6 B parameter model built on the rwkv6 architecture. It supports a maximum context length of 1 048 576 tokens and is released under the apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Efficient inference on modest GPUs
  • Flexible quantization options

Limits

  • No vision support
  • Requires 1 048 576 token context for full capability
  • License is apache‑2.0

Best for

  • Long‑form text generation
  • Context‑heavy dialogue systems
  • Fine‑tuning on custom corpora

Who it’s for. Developers and researchers needing a lightweight RWKV model with very large context. The model is suitable for projects that can run on GPUs with 8 GB or more VRAM and prefer open‑source licensing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.7 GB 1.2 GB
Fits Get file →
IQ3_XXS0.7 GB 1.3 GB
Fits Get file →
IQ3_S0.8 GB 1.4 GB
Fits Get file →
Q3_K_L0.8 GB 1.4 GB
Fits Get file →
Q3_K0.8 GB 1.4 GB
Fits Get file →
IQ4_XS0.9 GB 1.6 GB
Fits Get file →
IQ4_NL1.0 GB 1.6 GB
Fits Get file →
Q4_01.0 GB 1.6 GB
Fits Get file →
Q4_01.0 GB 1.6 GB
Fits Get file →
Q4_01.0 GB 1.6 GB
Fits Get file →
Q4_01.0 GB 1.6 GB
Fits Get file →
Q4_K_S1.0 GB 1.6 GB
Fits Get file →
Q4_K1.0 GB 1.6 GB
Fits Get file →
Q4_11.1 GB 1.7 GB
Fits Get file →
Q5_01.2 GB 1.8 GB
Fits Get file →
Q5_K_S1.2 GB 1.8 GB
Fits Get file →
Q5_K1.2 GB 1.8 GB
Fits Get file →
Q5_11.3 GB 1.9 GB
Fits Get file →
Q6_K1.4 GB 2.0 GB
Fits Get file →
Q8_01.7 GB 2.5 GB
Fits Get file →
BF163.2 GB 4.1 GB
Fits Get file →
F163.2 GB 4.1 GB
Fits Get file →
F326.4 GB 7.7 GB
Tight Get file →

For 8 GB VRAM, use Q4_0 (0.99 GB file, ~1.6 GB memory at 8 k context). For 12 GB VRAM, Q5_0 (1.17 GB file, ~1.8 GB memory) offers higher precision. If more memory is available, Q6_K (1.37 GB file, ~2 GB memory) provides better accuracy.

What GPU do you need for rwkv 6 finch 1b6?

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 Q8_0 (1.7 GB file, about 2.5 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.2 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F32 (6.4 GB file, about 7.7 GB in use).

Which rwkv 6 finch 1b6 quant should you choose?

Q4_K_S (1.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 0.7 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
Parameters1.6B
Layers24
Trained context1,048,576 tokens

Source

Quantized bylatestissue
FamilyRwkv
Licenseapache-2.0
Downloads (HF)1,945
Last updated2024-10-23

Frequently asked questions about rwkv 6 finch 1b6

How much VRAM does rwkv 6 finch 1b6 need?

About 1.6 GB at Q4_K_S 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 rwkv 6 finch 1b6 on an 8 GB GPU?

Yes, with F32: the 6.4 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of rwkv 6 finch 1b6 GGUF?

It depends on the quant: Q2_K is 0.7 GB, IQ3_XXS is 0.7 GB, IQ3_S is 0.8 GB, Q3_K_L is 0.8 GB, Q3_K is 0.8 GB, IQ4_XS is 0.9 GB and 17 more.

What context length does rwkv 6 finch 1b6 support?

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

Where can I download rwkv 6 finch 1b6 GGUF?

The files are on Hugging Face in the latestissue/rwkv-6-finch-1b6-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 rwkv 6 finch 1b6 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 rwkv 6 finch 1b6 on 8 GB VRAM?

Yes, the Q4_0 quantization requires about 1.6 GB VRAM at 8 k context, which fits within 8 GB.

Does the model support image inputs?

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 latestissue

All by latestissue →

More Rwkv models

All Rwkv →

Other tiny models

All tiny models →