QW

Qwen3.5 22B A3B Heretic Reap

QwenGGUF by mradermacherUpdated 2026-03-07
Download on Hugging Face
Parameters22.2B
Context256K
Layers40
Architectureqwen35moe
Smallest quant0.1 GB
Quick answer

Qwen3.5 22B A3B Heretic Reap needs about 14.8 GB of memory at Q4_K_M (a 13.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 0.1 GB to 18.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.5 22B A3B Heretic Reap – 22.2B parameter LLM with 262144 token context

Qwen3.5 22B A3B Heretic Reap is a 22.2B parameter model from the Qwen family. It supports a trained context length of 262144 tokens and is released under the apache-2.0 license. The model is a mixture of experts with 3 active parameters.

Good at

  • Large context handling
  • Mixture of experts architecture
  • Apache-2.0 licensed

Limits

  • No vision support indicated
  • Large memory requirement for higher quantizations
  • Requires GGUF format

Best for

  • Long‑form text generation
  • Complex reasoning tasks
  • Fine‑tuning on custom data

Who it’s for. Developers needing a large‑scale LLM with extended context for research or production. The model is suitable for those who can manage GGUF files and have sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.3 GB
Fits Get file →
IQ1_S4.8 GB 6.0 GB
Fits Get file →
IQ1_M5.3 GB 6.4 GB
Fits Get file →
IQ2_XXS6.1 GB 7.2 GB
Tight Get file →
IQ2_XS6.7 GB 7.9 GB
Tight Get file →
IQ2_S6.8 GB 8.0 GB
Too big Get file →
IQ2_M7.5 GB 8.7 GB
Too big Get file →
Q2_K_S7.8 GB 9.0 GB
Too big Get file →
Q2_K8.3 GB 9.5 GB
Too big Get file →
IQ3_XXS8.7 GB 9.9 GB
Too big Get file →
IQ3_XS9.3 GB 10.5 GB
Too big Get file →
Q3_K_S9.8 GB 11.0 GB
Too big Get file →
IQ3_S9.8 GB 11.0 GB
Too big Get file →
IQ3_M10.0 GB 11.2 GB
Too big Get file →
Q3_K_M10.8 GB 12.0 GB
Too big Get file →
Q3_K_L11.6 GB 12.8 GB
Too big Get file →
IQ4_XS12.0 GB 13.2 GB
Too big Get file →
Q4_012.7 GB 13.9 GB
Too big Get file →
Q4_K_S12.8 GB 14.0 GB
Too big Get file →
Q4_K_M13.6 GB 14.8 GB
Too big Get file →
Q4_114.0 GB 15.2 GB
Too big Get file →
Q5_K_S15.4 GB 16.6 GB
Too big Get file →
Q5_K_M15.9 GB 17.1 GB
Too big Get file →
Q6_K18.3 GB 19.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 13.59 GB, estimated 14.8 GB memory at 8 k context). For 12 GB VRAM, Q4_K_S (12.78 GB, 14 GB memory) is a good balance. Higher quantizations like Q5_K_M require more than 15 GB VRAM.

What GPU do you need for Qwen3.5 22B A3B Heretic Reap?

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 the main file (0.1 GB file, about 1.3 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ1_S (4.8 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_S (6.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_M (10.8 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (14.0 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 19.4 GB in use).

Which Qwen3.5 22B A3B Heretic Reap quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 22B A3B Heretic Reap: it balances file size and quality well. Here it is a 13.6 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 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

Architectureqwen35moe
Parameters22.2B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,165
Last updated2026-03-07

Frequently asked questions about Qwen3.5 22B A3B Heretic Reap

How much VRAM does Qwen3.5 22B A3B Heretic Reap need?

About 14.8 GB at Q4_K_M with an 8K context window. That is the 13.6 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 Qwen3.5 22B A3B Heretic Reap on an 8 GB GPU?

Yes, with IQ2_S: the 6.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 22B A3B Heretic Reap GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 4.8 GB, IQ1_M is 5.3 GB, IQ2_XXS is 6.1 GB, IQ2_XS is 6.7 GB, IQ2_S is 6.8 GB and 18 more.

What context length does Qwen3.5 22B A3B Heretic Reap 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 2.7 GB at 32K.

Where can I download Qwen3.5 22B A3B Heretic Reap GGUF?

The files are on Hugging Face in the mradermacher/Qwen3.5-22B-A3B-heretic-reap-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 Qwen3.5 22B A3B Heretic Reap 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 Qwen3.5 22B A3B Heretic Reap on 8 GB VRAM?

Use the Q4_K_M quantization; it estimates 14.8 GB memory at 8 k context, which is close to 8 GB but may need CPU fallback.

What license applies to this model?

The model is released under the apache-2.0 license.

Does this model support vision tasks?

No vision support is indicated in the provided facts.

Other GGUFs of Qwen3.5-22B-A3B-heretic-reap

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →