Jeesup svd safety l3 swift jbbcal2 remove40 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 13 quants, from 3.2 GB (Q2_K) to 16.1 GB (F16).
Swift‑SVD compressed Llama‑3‑8B‑Instruct with LoRA recovery
Jeesup svd safety l3 swift jbbcal2 remove40 is an 8.03 billion‑parameter Llama model compressed to 60 % of dense parameters. It uses Swift‑SVD dynamic rank allocation and SVD‑LLM stage‑2 LoRA for safety recovery. The checkpoint is a research artifact for safety‑utility trade‑offs.
Good at
- Research on SVD compression effects
- Safety‑degradation experiments
- LoRA recovery evaluation
Limits
- Not a general‑purpose chat model
- Safety‑degraded relative to Llama‑3‑8B‑Instruct
- Requires evaluation before use
Best for
- Safety research studies
- Compression impact testing
- Experimental safety calibration
Who it’s for. This model is intended for researchers and developers studying the effects of SVD compression on safety behaviour. It is not designed for general deployment and should be evaluated thoroughly before use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_S | 3.7 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_M | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 4.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 4.7 GB | 6.2 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q5_0 | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_S | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 6.6 GB | 8.2 GB | Too big | Get file → | |
| Q8_0 | 8.5 GB | 10.1 GB | Too big | Get file → | |
| F16 | 16.1 GB | 17.6 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (4.92 GB, 6.5 GB memory) is suitable. For 16 GB VRAM, Q5_K_M (5.73 GB, 7.3 GB memory) or Q6_K (6.6 GB, 8.2 GB memory) provide a balance between size and performance. Higher‑precision quants such as Q8_0 or F16 exceed typical VRAM limits.
What GPU do you need for Jeesup svd safety l3 swift jbbcal2 remove40?
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: the best quant that fits is Q3_K_L (4.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).
Which Jeesup svd safety l3 swift jbbcal2 remove40 quant should you choose?
Q4_K_M is the usual starting point for Jeesup svd safety l3 swift jbbcal2 remove40: it balances file size and quality well. Here it is a 4.9 GB file.
The Q8_0 file is 8.5 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 3.2 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
Frequently asked questions about Jeesup svd safety l3 swift jbbcal2 remove40
How much VRAM does Jeesup svd safety l3 swift jbbcal2 remove40 need?
About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Jeesup svd safety l3 swift jbbcal2 remove40 on an 8 GB GPU?
Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Jeesup svd safety l3 swift jbbcal2 remove40 GGUF?
It depends on the quant: Q2_K is 3.2 GB, Q3_K_S is 3.7 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, Q4_0 is 4.7 GB, Q4_K_S is 4.7 GB and 7 more.
What context length does Jeesup svd safety l3 swift jbbcal2 remove40 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download Jeesup svd safety l3 swift jbbcal2 remove40 GGUF?
The files are on Hugging Face in the tinyopsec/Jeesup-svd-safety-l3_swift_jbbcal2_remove40-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 Jeesup svd safety l3 swift jbbcal2 remove40 use?
Hugging Face lists the license as llama3. 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant uses 4.92 GB file size and requires approximately 6.5 GB memory at 8k context, which fits 8 GB VRAM.
Does this model support vision?
No, the model has no vision capabilities.
What license applies?
Meta Llama 3 Community License governs use of this derivative.