mythos fast needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 1.4 GB (Q2_K_L) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
Fine‑tuned VibeThinker‑3B for tool‑use and agentic tasks
mythos_fast is a 3.1B‑parameter model based on WeiboAI/VibeThinker‑3B. It is fine‑tuned on ~2,000,000 samples for tool‑calling, function‑calling, and agent‑style reasoning. The model is available in GGUF format for local inference with llama.cpp.
Good at
- Tool‑calling workflows
- Agentic task execution
- Multi‑step reasoning
Limits
- No vision support
- Performance depends on tool definition format
- No license information provided
Best for
- Local autonomous agents
- Function‑calling pipelines
- Multi‑step reasoning tasks
Who it’s for. Developers building local LLM agents that need tool‑use capabilities. Suitable for environments where inference must run on a single machine with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_L | 1.4 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.1 GB | Fits | Get file → | |
| BF16 | 6.2 GB | 7.0 GB | Fits | Get file → | |
| F16 | 6.2 GB | 7.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.93 GB file, ~2.7 GB memory at 8 k context). For 4 GB VRAM, use Q3_K_M (1.59 GB file, ~2.4 GB memory). For 2 GB VRAM, use Q2_K_L (1.35 GB file, ~2.2 GB memory). Memory estimates are approximate.
What GPU do you need for mythos fast?
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: the best quant that fits is Q6_K (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (6.2 GB file, about 7.0 GB in use).
Which mythos fast quant should you choose?
Q4_K_M is the usual starting point for mythos fast: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.3 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_L at 1.4 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 mythos fast
How much VRAM does mythos fast need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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 fast on an 8 GB GPU?
Yes, with BF16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of mythos fast GGUF?
It depends on the quant: Q2_K_L is 1.4 GB, Q3_K_M is 1.6 GB, Q4_K_M is 1.9 GB, Q5_K_M is 2.2 GB, Q6_K is 2.5 GB, Q8_0 is 3.3 GB and 2 more.
What context length does mythos fast support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download mythos fast GGUF?
The files are on Hugging Face in the Shadow0482/mythos_fast 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_fast on 8 GB VRAM?
Yes, the Q4_K_M quantized file is 1.93 GB and requires about 2.7 GB VRAM at 8 k context.
Does mythos_fast support vision?
No, the model is text‑only and has no vision capability.
What tool format does it expect?
It requires tool definitions that match the format used during fine‑tuning; results may vary otherwise.