Skaldic Gemma 4 E4B v9 needs about 6.5 GB of memory at Q4_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 4.6 GB (Q4_K_M) to 7.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Skaldic Gemma 4 E4B v9 – a 7.46B parameter multimodal LLM
Skaldic Gemma 4 E4B v9 is a 7.46B parameter model fine‑tuned for NPC planning in games. It supports text, image, and audio input and outputs text plans. The model is released under Apache‑2.0 and can run on recent GPUs.
Good at
- Multimodal reasoning
- Game NPC planning
- Text generation
Limits
- Requires 6.5GB VRAM for Q4_K_M at 8K context
- No native video support
- License is Apache‑2.0
Best for
- Local game AI agents
- Browser‑based LLM demos
- Low‑latency text generation
Who it’s for. Developers building game AI or local LLM applications who need a small, multimodal model that can run on consumer GPUs. The model is suitable for hobbyists and professionals who prefer open‑source weights and a permissive license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 4.6 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 4.6 GB (9 parts) | 6.5 GB | Fits | Get file → | |
| Q8_0 | 7.9 GB | 9.9 GB | Too big | Get file → |
For 8‑GB VRAM, use the Q4_K_M quantized file (4.58 GB, ~6.5 GB memory at 8K context). If more memory is available, the Q8_0 quantized file (7.95 GB, ~9.9 GB memory) offers higher precision. The Q4_K_M shard set also fits the same memory budget.
What GPU do you need for Skaldic Gemma 4 E4B v9?
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 (4.6 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.9 GB file, about 9.9 GB in use).
Which Skaldic Gemma 4 E4B v9 quant should you choose?
Q4_K_M is the usual starting point for Skaldic Gemma 4 E4B v9: it balances file size and quality well. Here it is a 4.6 GB file.
The Q8_0 file is 7.9 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Skaldic Gemma 4 E4B v9
How much VRAM does Skaldic Gemma 4 E4B v9 need?
About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.6 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 Skaldic Gemma 4 E4B v9 on an 8 GB GPU?
Yes, with Q4_K_M: the 4.6 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Skaldic Gemma 4 E4B v9 GGUF?
It depends on the quant: Q4_K_M is 4.6 GB, Q4_K_M is 4.6 GB, Q8_0 is 7.9 GB.
What context length does Skaldic Gemma 4 E4B v9 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 Skaldic Gemma 4 E4B v9 GGUF?
The files are on Hugging Face in the arc-director/Skaldic-Gemma-4-E4B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Skaldic Gemma 4 E4B v9 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 Skaldic Gemma 4 E4B on 8 GB VRAM?
Yes, the Q4_K_M quantized file is 4.58 GB and requires about 6.5 GB VRAM at 8K context, fitting within an 8 GB budget.
Does the model support audio input?
Audio is supported on the E4B variant, but the fine‑tuned Skaldic version focuses on text and image input for NPC planning.
What license does the model use?
The model is released under the Apache‑2.0 license, allowing free use and modification.