InternVL3 78B needs about 73.4 GB of memory at F16 (a 70.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 54.4 GB (Q5_K_M) to 77.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
InternVL3 78B is a 72.7B-parameter Internvl model in GGUF format, quantized by Userb1az. Its trained context length is 32K tokens. The repository has 5 quant files, from 54.4 GB (Q5_K_M) to 77.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| 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 → | |
| F16 | 70.2 GB | 73.4 GB | Too big | Get file → | |
| F16 | 75.2 GB | 78.3 GB | Too big | Get file → | |
| Q8_0 | 77.3 GB | 80.4 GB | Too big | Get file → |
What GPU do you need for InternVL3 78B?
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 InternVL3 78B quant should you choose?
F16 (70.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q5_K_M at 54.4 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about InternVL3 78B
How much VRAM does InternVL3 78B need?
About 73.4 GB at F16 with an 8K context window. That is the 70.2 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 InternVL3 78B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 57.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of InternVL3 78B GGUF?
It depends on the quant: Q5_K_M is 54.4 GB, Q6_K is 64.3 GB, F16 is 70.2 GB, F16 is 75.2 GB, Q8_0 is 77.3 GB.
What context length does InternVL3 78B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). 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 InternVL3 78B GGUF?
The files are on Hugging Face in the Userb1az/InternVL3-78B-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 InternVL3 78B 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.