Qwen3.5 122B A10B Heretic needs about 75.5 GB of memory at Q4_K_M (a 74.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.4 GB to 100.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3.5 122B A10B Heretic – a large Mixture‑of‑Experts model in GGUF format
Qwen3.5 122B A10B Heretic is a 122 billion‑parameter model with 10 billion active parameters. It uses a qwen35moe architecture and supports a 262,144‑token context window. The model is released under the Apache‑2.0 license and is available in multiple GGUF quantizations.
Good at
- Large‑scale text generation
- Complex reasoning tasks
- Multimodal understanding
Limits
- Requires high VRAM for full‑precision use
- No vision support in this GGUF release
- Large context length may exceed VRAM limits
Best for
- Enterprise‑grade language modeling
- Research on Mixture‑of‑Experts architectures
- High‑capacity chatbot deployments
Who it’s for. Developers and researchers needing a large, Mixture‑of‑Experts language model. The model is suitable for applications that can accommodate its memory footprint and do not require vision capabilities in the GGUF format.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 1.7 GB | Fits | Get file → | |
| IQ1_S | 24.8 GB | 26.1 GB | Too big | Get file → | |
| IQ1_M | 27.6 GB | 28.9 GB | Too big | Get file → | |
| IQ2_XXS | 32.2 GB | 33.5 GB | Too big | Get file → | |
| IQ2_XS | 35.9 GB | 37.2 GB | Too big | Get file → | |
| IQ2_S | 36.3 GB | 37.6 GB | Too big | Get file → | |
| IQ2_M | 39.9 GB | 41.2 GB | Too big | Get file → | |
| Q2_K_S | 41.7 GB | 43.0 GB | Too big | Get file → | |
| Q2_K | 44.6 GB | 45.9 GB | Too big | Get file → | |
| IQ3_XXS | 47.1 GB | 48.5 GB | Too big | Get file → | |
| IQ3_XS | 50.2 GB | 51.5 GB | Too big | Get file → | |
| Q3_K_S | 52.9 GB | 54.2 GB | Too big | Get file → | |
| IQ3_S | 52.9 GB | 54.2 GB | Too big | Get file → | |
| IQ3_M | 53.8 GB | 55.1 GB | Too big | Get file → | |
| Q3_K_M | 58.6 GB | 59.9 GB | Too big | Get file → | |
| Q3_K_L | 63.2 GB | 64.5 GB | Too big | Get file → | |
| IQ4_XS | 65.2 GB | 66.6 GB | Too big | Get file → | |
| Q4_0 | 69.3 GB | 70.6 GB | Too big | Get file → | |
| Q4_K_S | 69.6 GB | 70.9 GB | Too big | Get file → | |
| Q4_K_M | 74.2 GB | 75.5 GB | Too big | Get file → | |
| Q4_1 | 76.6 GB | 77.9 GB | Too big | Get file → | |
| Q5_K_S | 84.2 GB | 85.5 GB | Too big | Get file → | |
| Q5_K_M | 87.0 GB | 88.3 GB | Too big | Get file → | |
| Q6_K | 100.3 GB | 101.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (24.84 GB file, ~26 GB memory at 8k context). For 16 GB VRAM, IQ2_XS (35.89 GB file, ~37 GB memory) or Q2_K (44.58 GB file, ~46 GB memory). For 24 GB VRAM, Q3_K_M (58.6 GB file, ~60 GB memory) or Q4_K_M (74.21 GB file, ~76 GB memory). Estimates are approximate.
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: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 32 GB VRAM: the best quant that fits is IQ1_M (27.6 GB file, about 28.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q2_K (44.6 GB file, about 45.9 GB in use).
Which Qwen3.5 122B A10B Heretic quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 122B A10B Heretic: it balances file size and quality well. Here it is a 74.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.4 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
Source
Frequently asked questions about Qwen3.5 122B A10B Heretic
How much VRAM does Qwen3.5 122B A10B Heretic need?
About 75.5 GB at Q4_K_M with an 8K context window. That is the 74.2 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?
Yes, with the smaller files: the 0.4 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 122B A10B Heretic GGUF?
It depends on the quant: file is 0.4 GB, IQ1_S is 24.8 GB, IQ1_M is 27.6 GB, IQ2_XXS is 32.2 GB, IQ2_XS is 35.9 GB, IQ2_S is 36.3 GB and 18 more.
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 mradermacher/Qwen3.5-122B-A10B-heretic-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 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.
Can I run Qwen3.5 122B A10B Heretic on 8 GB VRAM?
No, the smallest quant requires at least 24.84 GB of storage and ~26 GB of VRAM at 8k context. 8 GB VRAM is insufficient.
Does this model support vision tasks?
The GGUF release does not include vision weights; it is a text‑only model.
What license applies to this model?
The model is released under the Apache‑2.0 license.