mythos needs about 4.5 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 6 quants, from 3.2 GB (Q3_K_M) to 5.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
Gemma‑4 E2B instruction‑tuned model with multimodal support
mythos is a 4.65 billion‑parameter Gemma‑4 model fine‑tuned on Opus 4.7. It supports text, image, and audio input and outputs text. The model is available in several GGUF quantizations for local deployment.
Good at
- Reasoning with chain‑of‑thought
- Multimodal input handling
- Instruction following
Limits
- No vision support in Q3_K_M
- Large VRAM needed for Q8_0
- License not specified
Best for
- Local chat assistants
- Multimodal data analysis
- Coding assistance
Who it’s for. Developers and researchers needing a compact, multimodal LLM for on‑device inference. The model is suitable for laptops and edge devices with limited VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 3.2 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_M | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q5_K_M | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q2_K_L | 3.7 GB | 4.7 GB | Fits | Get file → | |
| Q6_K | 3.8 GB | 4.9 GB | Fits | Get file → | |
| Q8_0 | 5.0 GB | 6.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q3_K_M (file size 3.2 GB, estimated 4.3 GB memory). For 12 GB VRAM, Q4_K_M (3.43 GB, 4.5 GB memory). If 16 GB VRAM is available, Q5_K_M (3.63 GB, 4.7 GB memory) offers better quality.
What GPU do you need for mythos?
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 Q6_K (3.8 GB file, about 4.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.0 GB file, about 6.1 GB in use).
Which mythos quant should you choose?
Q4_K_M is the usual starting point for mythos: it balances file size and quality well. Here it is a 3.4 GB file.
The Q8_0 file is 5.0 GB, about 1.4 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 Q3_K_M at 3.2 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 mythos
How much VRAM does mythos need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.4 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 mythos on an 8 GB GPU?
Yes, with Q8_0: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of mythos GGUF?
It depends on the quant: Q3_K_M is 3.2 GB, Q4_K_M is 3.4 GB, Q5_K_M is 3.6 GB, Q2_K_L is 3.7 GB, Q6_K is 3.8 GB, Q8_0 is 5.0 GB.
What context length does mythos support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download mythos GGUF?
The files are on Hugging Face in the Shadow0482/mythos repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run mythos on 8 GB VRAM?
Yes, the Q3_K_M quantization requires about 4.3 GB VRAM at 8K context, which fits in 8 GB VRAM.
Does mythos support image input?
Yes, the model is multimodal and can process images via the gemma‑4‑E2B‑it architecture.
What is the context window of mythos?
The base Gemma‑4 model supports up to 256K tokens, but the fine‑tuned version uses 8K context in the provided quantizations.