QW

RWKV6QwQ 32B Final 250307

QwenGGUF by mradermacherUpdated 2026-03-26
Download on Hugging Face
Parameters34.9B
Context1024K
Layers64
Architecturerwkv6qwen2
Smallest quant0.0 GB
Quick answer

RWKV6QwQ 32B Final 250307 needs about 26.0 GB of memory at Q4_K_M (a 22.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.0 GB to 30.3 GB (Q6_K).

RWKV6QwQ 32B Final 250307 – a large‑context RWKV model

RWKV6QwQ 32B Final 250307 is a 34.9B‑parameter RWKV model based on Qwen. It supports a context length of 1,048,576 tokens and is licensed under Apache‑2.0. The model is optimized for reasoning tasks.

Good at

  • Large context reasoning
  • High token capacity
  • Apache‑2.0 license

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Limited to ~30 languages

Best for

  • Long‑form text generation
  • Complex reasoning workflows
  • Research on large‑context models

Who it’s for. Developers and researchers who need a high‑capacity RWKV model for reasoning tasks and long‑context generation. The model is suitable for environments that can handle the memory requirements of the larger quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
IQ1_S9.4 GB 11.0 GB
Too big Get file →
IQ1_M10.1 GB 11.9 GB
Too big Get file →
IQ2_XXS11.4 GB 13.2 GB
Too big Get file →
IQ2_XS12.4 GB 14.4 GB
Too big Get file →
IQ2_S12.6 GB 14.6 GB
Too big Get file →
IQ2_M13.6 GB 15.7 GB
Too big Get file →
Q2_K_S14.0 GB 16.2 GB
Too big Get file →
Q2_K14.6 GB 16.9 GB
Too big Get file →
IQ3_XXS15.5 GB 17.8 GB
Too big Get file →
IQ3_XS16.5 GB 19.0 GB
Too big Get file →
IQ3_S17.1 GB 19.7 GB
Too big Get file →
Q3_K_S17.1 GB 19.7 GB
Too big Get file →
IQ3_M17.3 GB 19.9 GB
Too big Get file →
Q3_K_M18.4 GB 21.1 GB
Too big Get file →
Q3_K_L19.5 GB 22.3 GB
Too big Get file →
IQ4_XS20.6 GB 23.5 GB
Too big Get file →
Q4_021.7 GB 24.8 GB
Too big Get file →
Q4_K_S21.7 GB 24.9 GB
Too big Get file →
Q4_K_M22.8 GB 26.0 GB
Too big Get file →
Q4_123.7 GB 27.1 GB
Too big Get file →
Q5_K_S25.8 GB 29.4 GB
Too big Get file →
Q5_K_M26.4 GB 30.1 GB
Too big Get file →
Q6_K30.3 GB 34.4 GB
Too big Get file →

For 8‑GB VRAM use IQ1_S (9.4 GB file, 11 GB memory at 8k context). For 16‑GB VRAM use Q4_K_M (22.77 GB file, 26 GB memory). For 24‑GB VRAM use Q5_K_M (26.42 GB file, 30.1 GB memory). Estimates are approximate.

What GPU do you need for RWKV6QwQ 32B Final 250307?

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 (0.0 GB file, about 0.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ1_M (10.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_M (13.6 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (20.6 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (26.4 GB file, about 30.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (30.3 GB file, about 34.4 GB in use).

Which RWKV6QwQ 32B Final 250307 quant should you choose?

Q4_K_M is the usual starting point for RWKV6QwQ 32B Final 250307: it balances file size and quality well. Here it is a 22.8 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturerwkv6qwen2
Parameters34.9B
Layers64
Trained context1,048,576 tokens

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,711
Last updated2026-03-26

Frequently asked questions about RWKV6QwQ 32B Final 250307

How much VRAM does RWKV6QwQ 32B Final 250307 need?

About 26.0 GB at Q4_K_M with an 8K context window. That is the 22.8 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 RWKV6QwQ 32B Final 250307 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of RWKV6QwQ 32B Final 250307 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 9.4 GB, IQ1_M is 10.1 GB, IQ2_XXS is 11.4 GB, IQ2_XS is 12.4 GB, IQ2_S is 12.6 GB and 18 more.

What context length does RWKV6QwQ 32B Final 250307 support?

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

Where can I download RWKV6QwQ 32B Final 250307 GGUF?

The files are on Hugging Face in the mradermacher/RWKV6QwQ-32B-final-250307-i1-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 RWKV6QwQ 32B Final 250307 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?

Use the IQ1_S quantization; it requires about 11 GB memory at 8k context.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of QRWKV-QwQ-32B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →