Qwen2.5 VL 72B Instruct Heretic needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 29.8 GB (Q2_K) to 77.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Qwen2.5 VL 72B Instruct Heretic – large vision‑language model
Qwen2.5 VL 72B Instruct Heretic is a 72‑billion‑parameter vision‑language model. It supports image, video, and structured output tasks. The model is instruction‑tuned and available in multiple GGUF quantizations.
Good at
- Vision‑language reasoning
- Structured data extraction
- Long‑video comprehension
Limits
- Requires large VRAM for full precision
- No native vision‑to‑text API in llama.cpp
- License is other, not open source
Best for
- Image captioning with bounding boxes
- Invoice and form data extraction
- Video event detection
Who it’s for. Developers building advanced vision‑language applications who need a large model with structured output capabilities. The model is suitable for research and enterprise use where high accuracy on visual tasks is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 29.8 GB | 33.0 GB | Too big | Get file → | |
| Q3_K_S | 34.5 GB | 37.7 GB | Too big | Get file → | |
| Q3_K_M | 37.7 GB | 40.9 GB | Too big | Get file → | |
| Q3_K_L | 39.5 GB | 42.7 GB | Too big | Get file → | |
| IQ4_XS | 40.2 GB | 43.3 GB | Too big | Get file → | |
| Q4_K_S | 43.9 GB | 47.1 GB | Too big | Get file → | |
| Q4_K_M | 47.4 GB | 50.6 GB | Too big | Get file → | |
| Q5_K_S | 51.4 GB | 54.6 GB | Too big | Get file → | |
| Q5_K_M | 54.4 GB | 57.6 GB | Too big | Get file → | |
| Q6_K | 64.3 GB | 67.5 GB | Too big | Get file → | |
| Q8_0 | 77.3 GB | 80.4 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_S (43.89 GB file, ~47 GB memory at 8k context). For 16‑GB VRAM, Q5_K_S (51.38 GB file, ~55 GB memory) is a good balance. For 32‑GB VRAM, Q6_K (64.35 GB file, ~68 GB memory) offers higher fidelity.
What GPU do you need for Qwen2.5 VL 72B Instruct 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: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).
Which Qwen2.5 VL 72B Instruct Heretic quant should you choose?
Q4_K_M is the usual starting point for Qwen2.5 VL 72B Instruct Heretic: it balances file size and quality well. Here it is a 47.4 GB file.
The Q8_0 file is 77.3 GB, about 1.6 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 29.8 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 Qwen2.5 VL 72B Instruct Heretic
How much VRAM does Qwen2.5 VL 72B Instruct Heretic need?
About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 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 Qwen2.5 VL 72B Instruct Heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 33.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen2.5 VL 72B Instruct Heretic GGUF?
It depends on the quant: Q2_K is 29.8 GB, Q3_K_S is 34.5 GB, Q3_K_M is 37.7 GB, Q3_K_L is 39.5 GB, IQ4_XS is 40.2 GB, Q4_K_S is 43.9 GB and 5 more.
What context length does Qwen2.5 VL 72B Instruct Heretic support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Qwen2.5 VL 72B Instruct Heretic GGUF?
The files are on Hugging Face in the mradermacher/Qwen2.5-VL-72B-Instruct-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 Qwen2.5 VL 72B Instruct Heretic use?
Hugging Face lists the license as other. 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 Qwen2.5 VL 72B Instruct Heretic on 8 GB VRAM?
Only with the smallest quant, Q2_K, which still requires ~34 GB memory at 8k context, so 8 GB VRAM is insufficient.
Does this model support vision tasks in llama.cpp?
Yes, the model includes vision capabilities and can be used with llama.cpp via the provided GGUF files.
What is the context length of this model?
The model was trained with a context of 128,000 tokens.