QW

Qwen3.5 122B A10B heretic

QwenGGUF by SabomakoUpdated 2026-03-02
Download on Hugging Face
Parameters122B
Context256K
Layers48
Architectureqwen35moe
Smallest quant68.3 GB
Quick answer

Qwen3.5 122B A10B heretic needs about 131.2 GB of memory at Q8_0 (a 129.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 68.3 GB (MXFP4_MOE) to 244.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3.5 122B A10B heretic is a 122B-parameter Qwen model in GGUF format, quantized by Sabomako. Its trained context length is 256K tokens. The repository has 3 quant files, from 68.3 GB (MXFP4_MOE) to 244.3 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE68.3 GB (2 parts) 69.6 GB
Too big Get file →
Q8_0129.9 GB (4 parts) 131.2 GB
Too big Get file →
BF16244.3 GB (6 parts) 245.6 GB
Too big Get file →

What GPU do you need for Qwen3.5 122B A10B heretic?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Qwen3.5 122B A10B heretic quant should you choose?

Q8_0 (129.9 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is MXFP4_MOE at 68.3 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters122B (approximate, mixture of experts)
Active parameters10B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bySabomako
FamilyQwen
Licenseapache-2.0
Downloads (HF)103
Last updated2026-03-02

Frequently asked questions about Qwen3.5 122B A10B heretic

How much VRAM does Qwen3.5 122B A10B heretic need?

About 131.2 GB at Q8_0 with an 8K context window. That is the 129.9 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 122B A10B heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 69.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.5 122B A10B heretic GGUF?

It depends on the quant: MXFP4_MOE is 68.3 GB, Q8_0 is 129.9 GB, BF16 is 244.3 GB.

What context length does Qwen3.5 122B A10B heretic support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Qwen3.5 122B A10B heretic GGUF?

The files are on Hugging Face in the Sabomako/Qwen3.5-122B-A10B-heretic-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 122B A10B heretic 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.

Other GGUFs of Qwen3.5-122B-A10B-heretic

Similar models

Browse all →

More from Sabomako

All by Sabomako →

More Qwen models

All Qwen →

Other large models

All large models →