SAVER 0.8B needs about 1.6 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.5 GB (Q2_K) to 2.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
SAVER 0.8B – sparse video reasoning model
SAVER 0.8B is a reinforcement‑learning post‑trained model based on Qwen3.5‑0.8B. It is designed for sparse video question answering and temporal grounding. The model uses dense video views as training references to improve sparse‑frame inference.
Good at
- Sparse video reasoning
- Temporal grounding
- Efficient frame usage
Limits
- No vision support in GGUF
- License not specified
- No mixture of experts
Best for
- Video QA with limited frames
- Temporal grounding tasks
- Sparse‑frame inference
Who it’s for. Developers building video‑language applications that require efficient reasoning with few frames. Researchers exploring sparse video models may also find it useful.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_L | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ4_XS | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_S | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_S | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q8_0 | 1.1 GB | 2.0 GB | Fits | Get file → | |
| F16 | 2.0 GB | 2.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 0.67 GB, estimated memory 1.6 GB). If 4 GB VRAM is available, Q3_K_S (0.54 GB, 1.4 GB memory) is a good choice. For higher quality, Q5_K_M (0.75 GB, 1.7 GB memory) fits 8 GB VRAM. Estimates are approximate.
What GPU do you need for SAVER 0.8B?
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: the best quant that fits is F16 (2.0 GB file, about 2.9 GB in use).
Which SAVER 0.8B quant should you choose?
Q4_K_M is the usual starting point for SAVER 0.8B: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.1 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 0.5 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 SAVER 0.8B
How much VRAM does SAVER 0.8B need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.7 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 SAVER 0.8B on an 8 GB GPU?
Yes, with F16: the 2.0 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SAVER 0.8B GGUF?
It depends on the quant: Q2_K is 0.5 GB, Q3_K_S is 0.5 GB, Q3_K_M is 0.6 GB, Q3_K_L is 0.6 GB, IQ4_XS is 0.6 GB, Q4_K_S is 0.6 GB and 6 more.
What context length does SAVER 0.8B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download SAVER 0.8B GGUF?
The files are on Hugging Face in the mradermacher/SAVER-0.8B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run SAVER 0.8B on 8 GB VRAM?
Yes, Q4_K_M or Q5_K_M quantizations fit within 8 GB VRAM with estimated memory usage of 1.6–1.7 GB.
Does the model support vision tasks?
The GGUF version does not include vision support; the model is focused on sparse video reasoning.
What is the context length of this model?
The model was trained with 262144 context tokens.