Gemma-4-E4B-Nightcap 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 5.2 GB (Q4_0) to 8.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Gemma‑4‑E4B‑Nightcap: a role‑play focused 7.52B‑parameter model
Gemma‑4‑E4B‑Nightcap is a 7.52‑billion‑parameter language model fine‑tuned for grounded dialogue, character consistency, and comedic timing. It uses the Gemma‑4 architecture and was built by merging three community fine‑tunes. The model supports a 131072‑token context window and is available in multiple GGUF quantizations.
Good at
- Grounded character dialogue
- Consistent persona responses
- Creative role‑play scenarios
Limits
- No multimodal support
- Requires 8‑k context for memory estimates
- License is gemma
Best for
- Chatbots needing stable role‑play
- Creative writing assistants
- Character‑driven storytelling
Who it’s for. Developers and hobbyists who want a lightweight, text‑only model for role‑play and creative writing. The model is ideal for applications that need consistent character voices and comedic timing without the overhead of vision or audio towers.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 5.2 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_M | 5.3 GB | 7.2 GB | Tight | Get file → | |
| Q6_K | 6.2 GB | 8.1 GB | Too big | Get file → | |
| Q8_0 | 8.0 GB | 9.9 GB | Too big | Get file → |
For 8‑GB VRAM, Q4_0 (5.19 GB file, 7.1 GB memory at 8‑k context) or Q4_K_M (5.34 GB file, 7.2 GB memory) are suitable. If more VRAM is available, Q6_K (6.22 GB file, 8.1 GB memory) or Q8_0 (8.03 GB file, 9.9 GB memory) provide higher quality with acceptable memory usage. Estimates are approximate.
What GPU do you need for Gemma-4-E4B-Nightcap?
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 Q4_K_M (5.3 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
Which Gemma-4-E4B-Nightcap quant should you choose?
Q4_K_M is the usual starting point for Gemma-4-E4B-Nightcap: it balances file size and quality well. Here it is a 5.3 GB file.
The Q8_0 file is 8.0 GB, about 1.5 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 Q4_0 at 5.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma-4-E4B-Nightcap
How much VRAM does Gemma-4-E4B-Nightcap 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-Nightcap on an 8 GB GPU?
Yes, with Q4_K_M: the 5.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma-4-E4B-Nightcap GGUF?
It depends on the quant: Q4_0 is 5.2 GB, Q4_K_M is 5.3 GB, Q6_K is 6.2 GB, Q8_0 is 8.0 GB.
What context length does Gemma-4-E4B-Nightcap 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-Nightcap GGUF?
The files are on Hugging Face in the andyoneal/Gemma-4-E4B-Nightcap-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-Nightcap use?
Hugging Face lists the license as gemma. 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 Gemma‑4‑E4B‑Nightcap on 8 GB VRAM?
Yes, using Q4_0 or Q4_K_M quantizations will fit within 8 GB VRAM, with memory usage around 7.1–7.2 GB at 8‑k context.
Does this model support vision or audio?
No, the GGUF conversion drops the multimodal towers; it is text‑only.
What sampler settings are recommended?
Use temp 1.0, min‑p 0.02, no repetition penalties; temp 0.8/top‑p 0.95 also works.