gemma 4 E4B it SDFT Heretic RP needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 5.0 GB (Q3_K_L) to 6.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Gemma 4 E4B it SDFT Heretic RP – RP‑enhanced Gemma 4 for narrative roles
Gemma 4 E4B it SDFT Heretic RP is a 7.5 billion‑parameter model tuned for roleplay. It supports vision and roleplay abilities and is released under Apache‑2.0. The model is available as GGUF quantizations for local inference.
Good at
- Roleplay scene continuation
- Character and world continuity
- Multi‑turn RP context
Limits
- No safety guardrails – use responsibly
- Vision support only via shared projector
- Large context but limited to 131072 tokens
Best for
- Dark fantasy narration
- Game Master scene continuation
- NPC dialogue generation
Who it’s for. Researchers, developers, and hobbyists who need a roleplay‑focused Gemma 4 model for local inference. The model is intended for evaluation, research, and narrative experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 5.0 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_M | 5.3 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_M | 5.8 GB | 7.7 GB | Tight | Get file → | |
| Q6_K | 6.2 GB | 8.1 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (5.34 GB) is recommended. If 12 GB VRAM is available, Q5_K_M (5.76 GB) offers higher quality. Q6_K (6.22 GB) gives the best prose stability but requires more memory. Q3_K_L (5.02 GB) is the lowest‑memory option.
What GPU do you need for gemma 4 E4B it SDFT Heretic RP?
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 Q5_K_M (5.8 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.2 GB file, about 8.1 GB in use).
Which gemma 4 E4B it SDFT Heretic RP quant should you choose?
Q4_K_M is the usual starting point for gemma 4 E4B it SDFT Heretic RP: it balances file size and quality well. Here it is a 5.3 GB file.
If memory is tight, the smallest file is Q3_K_L at 5.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about gemma 4 E4B it SDFT Heretic RP
How much VRAM does gemma 4 E4B it SDFT Heretic RP need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 gemma 4 E4B it SDFT Heretic RP on an 8 GB GPU?
Yes, with Q5_K_M: the 5.8 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of gemma 4 E4B it SDFT Heretic RP GGUF?
It depends on the quant: Q3_K_L is 5.0 GB, Q4_K_M is 5.3 GB, Q5_K_M is 5.8 GB, Q6_K is 6.2 GB.
What context length does gemma 4 E4B it SDFT Heretic RP support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download gemma 4 E4B it SDFT Heretic RP GGUF?
The files are on Hugging Face in the Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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 gemma 4 E4B it SDFT Heretic RP 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 this model on 8 GB VRAM?
Yes, Q4_K_M requires 7.2 GB at 8k context, which fits 8 GB VRAM with some headroom.
Does this model support vision?
Yes, but only with the shared multimodal projector file; the base model itself is text‑only.
What license applies to this model?
The model is released under Apache‑2.0, allowing free use and modification.