Jun Lora v2 SAFETENSOR needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Jun Lora v2 SAFETENSOR – 11.9B Gemma4 LoRA fine‑tune for character conversation
Jun Lora v2 SAFETENSOR is a 11.9B Gemma4 LoRA fine‑tune trained on synthetic multi‑turn dialogue from the visual novel *My Dystopian Robot Girlfriend*. It preserves the base model’s reasoning and instruction‑following while capturing Jun’s personality and emotional nuance. The model is available in FP16 SafeTensors and multiple GGUF quantizations.
Good at
- Character‑consistent multi‑turn chat
- Role‑play with Jun persona
- Tool‑enabled conversations
Limits
- Specialized for Jun; not a general assistant
- Requires ~24 GB VRAM for FP16; lower VRAM needs GGUF
- No vision support
Best for
- AI companion webapps
- Interactive fiction engines
- Research on character‑faithful fine‑tuning
Who it’s for. Developers building AI companions or interactive fiction that require a consistent character voice. Researchers exploring fine‑tuning on small, high‑quality datasets may also benefit.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.8 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 18.9 GB | Too big | Get file → | |
| Q3_K_M | 6.1 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_L | 6.6 GB | 20.0 GB | Too big | Get file → | |
| IQ4_XS | 6.7 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_S | 7.0 GB | 20.4 GB | Too big | Get file → | |
| Q4_K_M | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 8.5 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 23.2 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (4.83 GB). For 12 GB VRAM, Q3_K_S (5.53 GB) or Q3_K_M (6.09 GB). For 16 GB VRAM, Q4_K_S (7.02 GB) or Q4_K_M (7.38 GB). Higher‑quality quants such as Q5_K_M (8.55 GB) or Q6_K (9.79 GB) fit 20 GB VRAM setups. Estimates are approximate.
What GPU do you need for Jun Lora v2 SAFETENSOR?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
Which Jun Lora v2 SAFETENSOR quant should you choose?
Q4_K_M is the usual starting point for Jun Lora v2 SAFETENSOR: it balances file size and quality well. Here it is a 7.4 GB file.
The Q8_0 file is 12.7 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.
If memory is tight, the smallest file is Q2_K at 4.8 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 Jun Lora v2 SAFETENSOR
How much VRAM does Jun Lora v2 SAFETENSOR need?
About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 Jun Lora v2 SAFETENSOR on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Jun Lora v2 SAFETENSOR GGUF?
It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.1 GB, Q3_K_L is 6.6 GB, IQ4_XS is 6.7 GB, Q4_K_S is 7.0 GB and 5 more.
What context length does Jun Lora v2 SAFETENSOR support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download Jun Lora v2 SAFETENSOR GGUF?
The files are on Hugging Face in the mradermacher/Jun-Lora-v2-SAFETENSOR-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 Jun Lora v2 SAFETENSOR 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 Jun Lora v2 on 8 GB VRAM?
Yes, the Q2_K quant is 4.83 GB and requires about 18.2 GB memory at 8k context, which fits 8 GB VRAM with efficient batching.
Does this model support vision tasks?
No, the model is trained for text only and has no vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.