RD

RDT2 VQ

RdtGGUF by mradermacherUpdated 2025-10-02
Download on Hugging Face
Parameters7.6B
Context125K
Layers28
Architectureqwen2vl
Smallest quant3.0 GB
Quick answer

RDT2 VQ needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 3.0 GB (Q2_K) to 15.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

RDT2 VQ – Vision‑Language‑Action model for bimanual robot manipulation

RDT2 VQ is an autoregressive Vision‑Language‑Action model based on Qwen2.5‑VL‑7B‑Instruct. It predicts short‑horizon relative action chunks from two wrist‑camera RGB images and a short instruction. The model uses a Residual VQ tokenizer for compact action codes.

Good at

  • Vision‑language instruction following
  • Zero‑shot cross‑embodiment for bimanual robots
  • Compact action representation

Limits

  • No vision support beyond two RGB cameras
  • Large context requires high VRAM
  • License is Apache‑2.0

Best for

  • Robot manipulation policy generation
  • Simulated robot training
  • Real‑time closed‑loop control

Who it’s for. Developers building vision‑guided bimanual robot systems. Researchers needing a lightweight action tokenizer for open‑vocabulary skills.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB 4.0 GB
Fits Get file →
Q3_K_S3.5 GB 4.5 GB
Fits Get file →
Q3_K_M3.8 GB 4.8 GB
Fits Get file →
Q3_K_L4.1 GB 5.1 GB
Fits Get file →
IQ4_XS4.3 GB 5.2 GB
Fits Get file →
Q4_K_S4.5 GB 5.4 GB
Fits Get file →
Q4_K_M4.7 GB 5.7 GB
Fits Get file →
Q5_K_S5.3 GB 6.3 GB
Fits Get file →
Q5_K_M5.4 GB 6.4 GB
Fits Get file →
Q6_K6.3 GB 7.2 GB
Tight Get file →
Q8_08.1 GB 9.1 GB
Too big Get file →
F1615.2 GB 16.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.68 GB, memory 5.7 GB). For 12 GB VRAM, Q5_K_M (5.44 GB, 6.4 GB). For 16 GB VRAM, Q6_K (6.25 GB, 7.2 GB).

What GPU do you need for RDT2 VQ?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 Q2_K (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.2 GB file, about 16.2 GB in use).

Which RDT2 VQ quant should you choose?

Q4_K_M is the usual starting point for RDT2 VQ: it balances file size and quality well. Here it is a 4.7 GB file.

The Q8_0 file is 8.1 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 Q2_K at 3.0 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

Architectureqwen2vl
Parameters7.6B
Layers28
Trained context128,000 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
FamilyRdt
Licenseapache-2.0
Downloads (HF)757
Last updated2025-10-02

Frequently asked questions about RDT2 VQ

How much VRAM does RDT2 VQ need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 RDT2 VQ on an 8 GB GPU?

Yes, with Q6_K: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of RDT2 VQ GGUF?

It depends on the quant: Q2_K is 3.0 GB, Q3_K_S is 3.5 GB, Q3_K_M is 3.8 GB, Q3_K_L is 4.1 GB, IQ4_XS is 4.3 GB, Q4_K_S is 4.5 GB and 6 more.

What context length does RDT2 VQ support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download RDT2 VQ GGUF?

The files are on Hugging Face in the mradermacher/RDT2-VQ-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 RDT2 VQ 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 RDT2 VQ on 8 GB VRAM?

Yes, using the Q4_K_M quantized file which requires approximately 5.7 GB of VRAM at 8k context.

Does RDT2 VQ support multi‑GPU inference?

The model is designed for single‑GPU deployment; multi‑GPU scaling is not documented.

What license applies to RDT2 VQ?

The model is released under the Apache‑2.0 license.

Other GGUFs of RDT2-VQ

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rdt models

All Rdt →

Other small models

All small models →