QW

JoyFox-Qwen3.6-35B-A3B-RP-Aggressive

QwenGGUF by joyfoxUpdated 2026-08-04
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant20.2 GB
Quick answer

JoyFox-Qwen3.6-35B-A3B-RP-Aggressive needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 20.2 GB (Q4_0) to 37.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

JoyFox-Qwen3.6-35B-A3B-RP-Aggressive: roleplay‑focused multimodal Mixture‑of‑Experts model

JoyFox-Qwen3.6-35B-A3B-RP-Aggressive is a 35 B parameter Qwen3.6 variant with 3 B active experts. It supports vision and roleplay, offering sustained character voice and direct instruction following. The model retains a native context length of 262,144 tokens and can be extended up to 1,010,000 tokens.

Good at

  • Roleplay with sustained character voice
  • Direct instruction following
  • Long‑context creative dialogue

Limits

  • Vision support only, no text‑to‑image
  • Requires large VRAM for full context
  • Apache‑2.0 license limits commercial use without attribution

Best for

  • Interactive storytelling
  • Chatbot character simulation
  • Creative writing assistance

Who it’s for. Developers building role‑playing chatbots or creative writing tools who need a multimodal model with strong character consistency. The model is suitable for applications that can handle the memory demands of a 35 B parameter Mixture‑of‑Experts architecture.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_020.2 GB 21.4 GB
Too big Get file →
Q4_K_S20.4 GB 21.6 GB
Too big Get file →
Q4_K_M21.7 GB 22.9 GB
Too big Get file →
Q4_122.4 GB 23.6 GB
Too big Get file →
Q5_024.6 GB 25.8 GB
Too big Get file →
Q5_K_S24.6 GB 25.8 GB
Too big Get file →
Q5_K_M25.3 GB 26.5 GB
Too big Get file →
Q5_126.7 GB 27.9 GB
Too big Get file →
Q6_K29.2 GB 30.4 GB
Too big Get file →
Q8_037.8 GB 39.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (20.19 GB file, ~21.4 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (21.71 GB file, ~22.9 GB memory) is a good balance. If 16 GB VRAM is available, Q5_0 (24.56 GB file, ~25.8 GB memory) offers higher precision.

What GPU do you need for JoyFox-Qwen3.6-35B-A3B-RP-Aggressive?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_1 (22.4 GB file, about 23.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.2 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).

Which JoyFox-Qwen3.6-35B-A3B-RP-Aggressive quant should you choose?

Q4_K_M is the usual starting point for JoyFox-Qwen3.6-35B-A3B-RP-Aggressive: it balances file size and quality well. Here it is a 21.7 GB file.

The Q8_0 file is 37.8 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 Q4_0 at 20.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters35.5B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized byjoyfox
FamilyQwen
Licenseapache-2.0
Downloads (HF)9,196
Last updated2026-08-04

Frequently asked questions about JoyFox-Qwen3.6-35B-A3B-RP-Aggressive

How much VRAM does JoyFox-Qwen3.6-35B-A3B-RP-Aggressive need?

About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 JoyFox-Qwen3.6-35B-A3B-RP-Aggressive on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of JoyFox-Qwen3.6-35B-A3B-RP-Aggressive GGUF?

It depends on the quant: Q4_0 is 20.2 GB, Q4_K_S is 20.4 GB, Q4_K_M is 21.7 GB, Q4_1 is 22.4 GB, Q5_0 is 24.6 GB, Q5_K_S is 24.6 GB and 4 more.

What context length does JoyFox-Qwen3.6-35B-A3B-RP-Aggressive support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.

Where can I download JoyFox-Qwen3.6-35B-A3B-RP-Aggressive GGUF?

The files are on Hugging Face in the joyfox/JoyFox-Qwen3.6-35B-A3B-RP-Aggressive repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does JoyFox-Qwen3.6-35B-A3B-RP-Aggressive 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 Q4_0 quantized file; it requires about 21.4 GB of VRAM at 8 k context, which exceeds 8 GB, so it is not feasible without further optimization.

Does this model support text‑to‑image generation?

No, the model supports vision input but does not generate images.

What license applies to this model?

The model is released under the Apache‑2.0 license, requiring attribution for commercial use.

Other GGUFs of Qwen3.6-35B-A3B

Similar models

Browse all →

More from joyfox

All by joyfox →

More Qwen models

All Qwen →

Other large models

All large models →