TEMPURA Qwen2.5 VL 3B s2 needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.3 GB (Q2_K) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
TEMPURA Qwen2.5 VL 3B s2 – a 3.09B parameter vision‑language model
TEMPURA Qwen2.5 VL 3B s2 is a 3.09B parameter video‑language model based on Qwen2VL. It supports vision and tools and is fine‑tuned for temporal grounding and highlight detection in videos. The model is available in multiple GGUF quantizations.
Good at
- Vision‑language reasoning
- Temporal grounding
- Highlight detection
Limits
- No vision support beyond video
- Large memory requirement for higher quants
- License: non‑commercial research use
Best for
- Video summarization
- Event extraction
- Temporal question answering
Who it’s for. Researchers and developers needing fine‑grained temporal understanding in videos. The model is suitable for academic projects and prototypes that can run on GPUs with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 2.5 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.1 GB | Fits | Get file → | |
| F16 | 6.2 GB | 7.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.93 GB file, ~2.7 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (2.22 GB file, ~3 GB memory) is a good balance. If more VRAM is available, Q6_K or Q8_0 provide higher quality at the cost of memory.
What GPU do you need for TEMPURA Qwen2.5 VL 3B s2?
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: the best quant that fits is Q6_K (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).
Which TEMPURA Qwen2.5 VL 3B s2 quant should you choose?
Q4_K_M is the usual starting point for TEMPURA Qwen2.5 VL 3B s2: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.3 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.
If memory is tight, the smallest file is Q2_K at 1.3 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 TEMPURA Qwen2.5 VL 3B s2
How much VRAM does TEMPURA Qwen2.5 VL 3B s2 need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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 TEMPURA Qwen2.5 VL 3B s2 on an 8 GB GPU?
Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of TEMPURA Qwen2.5 VL 3B s2 GGUF?
It depends on the quant: Q2_K is 1.3 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.6 GB, Q3_K_L is 1.7 GB, IQ4_XS is 1.8 GB, Q4_K_S is 1.8 GB and 6 more.
What context length does TEMPURA Qwen2.5 VL 3B s2 support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download TEMPURA Qwen2.5 VL 3B s2 GGUF?
The files are on Hugging Face in the mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-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 TEMPURA Qwen2.5 VL 3B s2 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 TEMPURA Qwen2.5 VL 3B s2 on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.7 GB of VRAM at 8k context, which fits within an 8 GB GPU.
Does the model support image input?
The model supports vision input for video frames but is not designed for static image-only tasks.
Is the model free to use?
The model is licensed under the Qwen Research License for non‑commercial research use.