Heretic Qwen3 VL 235B A22B Instruct needs about 144.2 GB of memory at Q4_K_M (a 142.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 85.7 GB (Q2_K) to 249.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.
Heretic Qwen3 VL 235B A22B Instruct – a large multimodal instruction model
Heretic Qwen3 VL 235B A22B Instruct is a 235 billion‑parameter Qwen3‑VL model with 22 billion active mixture‑of‑experts parameters. It supports vision and tool usage and is available in multiple GGUF quantizations.
Good at
- Vision‑enabled instruction following
- Tool‑aware responses
- Large context handling
Limits
- Requires large VRAM (≈140 GB for Q4_K_M at 8k context)
- No built‑in vision support for non‑GGUF runtimes
- License is apache‑2.0
Best for
- Image‑captioning with instructions
- Automated tool invocation
- Long‑form multimodal dialogue
Who it’s for. Developers and researchers needing a multimodal instruction model with tool support. The model is open‑source under apache‑2.0 and can be run locally with GGUF-compatible runtimes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 85.7 GB | 87.8 GB | Too big | Get file → | |
| Q3_K_S | 101.4 GB | 103.5 GB | Too big | Get file → | |
| Q3_K_M | 112.4 GB | 114.5 GB | Too big | Get file → | |
| Q3_K_L | 121.8 GB | 123.9 GB | Too big | Get file → | |
| IQ4_XS | 126.7 GB | 128.7 GB | Too big | Get file → | |
| Q4_K_S | 133.7 GB | 135.8 GB | Too big | Get file → | |
| Q4_K_M | 142.2 GB | 144.2 GB | Too big | Get file → | |
| Q5_K_S | 161.9 GB | 164.0 GB | Too big | Get file → | |
| Q5_K_M | 166.8 GB | 168.9 GB | Too big | Get file → | |
| Q6_K | 193.0 GB | 195.1 GB | Too big | Get file → | |
| Q8_0 | 249.9 GB | 252.0 GB | Too big | Get file → |
For a 8 GB VRAM machine, the smallest quant is Q2_K (85.69 GB file, 87.8 GB memory at 8k context). For moderate memory budgets (~140 GB), Q4_K_M (142.15 GB file, 144.2 GB memory) is a good balance. Higher‑quality quants such as Q5_K_M or Q6_K require 168.9 GB or 195.1 GB respectively.
What GPU do you need for Heretic Qwen3 VL 235B A22B Instruct?
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 Heretic Qwen3 VL 235B A22B Instruct quant should you choose?
Q4_K_M is the usual starting point for Heretic Qwen3 VL 235B A22B Instruct: it balances file size and quality well. Here it is a 142.2 GB file.
The Q8_0 file is 249.9 GB, about 1.8 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 Q2_K at 85.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Heretic Qwen3 VL 235B A22B Instruct
How much VRAM does Heretic Qwen3 VL 235B A22B Instruct need?
About 144.2 GB at Q4_K_M with an 8K context window. That is the 142.2 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 Heretic Qwen3 VL 235B A22B Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 87.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Heretic Qwen3 VL 235B A22B Instruct GGUF?
It depends on the quant: Q2_K is 85.7 GB, Q3_K_S is 101.4 GB, Q3_K_M is 112.4 GB, Q3_K_L is 121.8 GB, IQ4_XS is 126.7 GB, Q4_K_S is 133.7 GB and 5 more.
What context length does Heretic Qwen3 VL 235B A22B Instruct support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.
Where can I download Heretic Qwen3 VL 235B A22B Instruct GGUF?
The files are on Hugging Face in the mradermacher/Heretic-Qwen3-VL-235B-A22B-Instruct-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 Heretic Qwen3 VL 235B A22B Instruct 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?
No. Even the smallest quant requires 87.8 GB of VRAM at 8k context. You need a machine with at least 140 GB of VRAM for Q4_K_M.
Does this model support vision?
Yes. It has detected abilities for vision and tools.
Is the model open source?
Yes, it is released under the apache‑2.0 license.