Molmo2 8B needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 5.0 GB (Q4_K_M) to 16.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Molmo2 8B – open vision‑language model with Qwen3 backbone
Molmo2 8B is an 8.19 billion‑parameter multimodal model based on Qwen3-8B. It supports image, video, and multi‑image understanding using a SigLIP 2 vision encoder. The model is licensed under Apache‑2.0 and is available as GGUF files.
Good at
- Vision‑language grounding
- Short‑video QA
- Multi‑image captioning
Limits
- No vision support in older GGUFs
- Large VRAM needed for high context
- Requires Apache‑2.0 compliance
Best for
- Research on multimodal benchmarks
- Educational demos of vision‑language models
- Video question answering prototypes
Who it’s for. Researchers and developers needing an open, multimodal model for image and video tasks. The model is suitable for academic and non‑commercial use under Apache‑2.0.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.0 GB | 6.7 GB | Fits | Get file → | |
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → | |
| F16 | 16.4 GB | 18.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (5.03 GB file, 6.7 GB estimated memory). Q8_0 (8.71 GB file, 10.4 GB memory) fits 12 GB VRAM. F16 (16.39 GB file, 18.1 GB memory) requires 20 GB VRAM or more. Estimates are approximate.
What GPU do you need for Molmo2 8B?
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: the best quant that fits is Q4_K_M (5.0 GB file, about 6.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (16.4 GB file, about 18.1 GB in use).
Which Molmo2 8B quant should you choose?
Q4_K_M is the usual starting point for Molmo2 8B: it balances file size and quality well. Here it is a 5.0 GB file.
The Q8_0 file is 8.7 GB, about 1.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Molmo2 8B
How much VRAM does Molmo2 8B need?
About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Molmo2 8B on an 8 GB GPU?
Yes, with Q4_K_M: the 5.0 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Molmo2 8B GGUF?
It depends on the quant: Q4_K_M is 5.0 GB, Q8_0 is 8.7 GB, F16 is 16.4 GB.
What context length does Molmo2 8B support?
The GGUF header lists a trained context length of 36,864 tokens (36K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Molmo2 8B GGUF?
The files are on Hugging Face in the mu2solutions/Molmo2-8B-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 Molmo2 8B 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 Molmo2 8B on 8 GB VRAM?
Yes, using the Q4_K_M quantized file which is 5.03 GB and requires about 6.7 GB of VRAM at 8k context.
Does the model support video input?
Yes, it supports short and long video understanding and grounding tasks.
What license applies to the GGUF files?
The GGUF files are licensed under Apache‑2.0, same as the source model.