InternVL3_5 38B needs about 22.4 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 12.3 GB (Q2_K) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
InternVL3_5 38B – a 32.8B multimodal model with coding and vision abilities
InternVL3_5 38B is a 32.8B parameter model in the InternVL family. It supports coding and vision tasks and is available in multiple GGUF quantizations. The model was released under the apache-2.0 license and can be run with llama.cpp.
Good at
- Coding tasks
- Vision inference
- Multimodal reasoning
Limits
- No vision support in some quant types
- Large VRAM required for higher quality quants
- License is apache-2.0
Best for
- Code generation with image context
- Image captioning
- Multimodal question answering
Who it’s for. Developers and researchers needing a large multimodal model for coding and vision tasks. The model is open‑source and can be integrated into custom inference pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.3 GB | 15.0 GB | Too big | Get file → | |
| Q3_K_S | 14.4 GB | 17.0 GB | Too big | Get file → | |
| Q3_K_M | 16.0 GB | 18.6 GB | Too big | Get file → | |
| Q3_K_L | 17.3 GB | 20.0 GB | Too big | Get file → | |
| IQ4_XS | 17.9 GB | 20.5 GB | Too big | Get file → | |
| Q4_K_S | 18.8 GB | 21.4 GB | Too big | Get file → | |
| Q4_K_M | 19.8 GB | 22.4 GB | Too big | Get file → | |
| Q5_K_S | 22.6 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_M | 23.2 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 26.9 GB | 29.5 GB | Too big | Get file → | |
| Q8_0 | 34.8 GB | 37.5 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (12.34 GB file, ~15 GB memory). For 12 GB VRAM use Q3_K_S (14.39 GB file, ~17 GB memory). For 16 GB VRAM use Q4_K_M (19.76 GB file, ~22.4 GB memory).
What GPU do you need for InternVL3_5 38B?
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: the best quant that fits is Q2_K (12.3 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (19.8 GB file, about 22.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).
Which InternVL3_5 38B quant should you choose?
Q4_K_M is the usual starting point for InternVL3_5 38B: it balances file size and quality well. Here it is a 19.8 GB file.
The Q8_0 file is 34.8 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 12.3 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
Source
Frequently asked questions about InternVL3_5 38B
How much VRAM does InternVL3_5 38B need?
About 22.4 GB at Q4_K_M with an 8K context window. That is the 19.8 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_5 38B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of InternVL3_5 38B GGUF?
It depends on the quant: Q2_K is 12.3 GB, Q3_K_S is 14.4 GB, Q3_K_M is 16.0 GB, Q3_K_L is 17.3 GB, IQ4_XS is 17.9 GB, Q4_K_S is 18.8 GB and 5 more.
What context length does InternVL3_5 38B support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download InternVL3_5 38B GGUF?
The files are on Hugging Face in the mradermacher/InternVL3_5-38B-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_5 38B 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 InternVL3_5 38B on 8 GB VRAM?
Yes, the Q2_K quant uses 12.34 GB file and requires about 15 GB memory at 8 k context.
Does the model support vision tasks?
Yes, the model has detected vision ability and can process images.