MixTAO-19B-pass needs about 13.7 GB of memory at Q4_K_M (a 11.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 4.1 GB (IQ1_S) to 15.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
MixTAO-19B-pass – 19.2B parameter Mixtao model in GGUF format
MixTAO-19B-pass is a 19.2B parameter Mixtao model based on the llama architecture. It supports a 32768 token context window and is released under the apache-2.0 license. The model is available in multiple quantizations for different memory budgets.
Good at
- Large context handling
- Mixture of experts architecture
- High parameter count
Limits
- No vision support
- Requires 8.2k context for estimates
- License is apache-2.0
Best for
- Long‑form content generation
- Complex reasoning tasks
- Fine‑tuning with limited VRAM
Who it’s for. Developers and researchers needing a large‑parameter LLM with extended context. The model is suitable for local deployment using llama.cpp and GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.1 GB | 6.2 GB | Fits | Get file → | |
| IQ1_M | 4.5 GB | 6.6 GB | Fits | Get file → | |
| IQ2_XXS | 5.1 GB | 7.2 GB | Tight | Get file → | |
| IQ2_XS | 5.7 GB | 7.8 GB | Tight | Get file → | |
| IQ2_S | 5.9 GB | 8.0 GB | Tight | Get file → | |
| IQ2_M | 6.4 GB | 8.5 GB | Too big | Get file → | |
| Q2_K | 7.1 GB | 9.2 GB | Too big | Get file → | |
| IQ3_XXS | 7.4 GB | 9.5 GB | Too big | Get file → | |
| IQ3_XS | 7.9 GB | 10.0 GB | Too big | Get file → | |
| Q3_K_S | 8.3 GB | 10.4 GB | Too big | Get file → | |
| IQ3_S | 8.3 GB | 10.4 GB | Too big | Get file → | |
| IQ3_M | 8.5 GB | 10.6 GB | Too big | Get file → | |
| Q3_K_M | 9.2 GB | 11.3 GB | Too big | Get file → | |
| Q3_K_L | 10.0 GB | 12.1 GB | Too big | Get file → | |
| IQ4_XS | 10.3 GB | 12.4 GB | Too big | Get file → | |
| Q4_0 | 10.9 GB | 13.0 GB | Too big | Get file → | |
| Q4_K_S | 10.9 GB | 13.0 GB | Too big | Get file → | |
| Q4_K_M | 11.6 GB | 13.7 GB | Too big | Get file → | |
| Q5_K_S | 13.2 GB | 15.3 GB | Too big | Get file → | |
| Q5_K_M | 13.6 GB | 15.7 GB | Too big | Get file → | |
| Q6_K | 15.7 GB | 17.9 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (est. 6.2 GB) or IQ1_M (6.6 GB). For 12‑GB VRAM, IQ4_K_S (13 GB) or Q4_K_M (13.7 GB) fit. For 16‑GB VRAM, Q5_K_S (15.3 GB) or Q5_K_M (15.7 GB) are recommended. Memory estimates are approximate.
What GPU do you need for MixTAO-19B-pass?
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 IQ2_S (5.9 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q3_K_M (9.2 GB file, about 11.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (13.6 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (15.7 GB file, about 17.9 GB in use).
Which MixTAO-19B-pass quant should you choose?
Q4_K_M is the usual starting point for MixTAO-19B-pass: it balances file size and quality well. Here it is a 11.6 GB file.
If memory is tight, the smallest file is IQ1_S at 4.1 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 MixTAO-19B-pass
How much VRAM does MixTAO-19B-pass need?
About 13.7 GB at Q4_K_M with an 8K context window. That is the 11.6 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 MixTAO-19B-pass on an 8 GB GPU?
Yes, with IQ2_S: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MixTAO-19B-pass GGUF?
It depends on the quant: IQ1_S is 4.1 GB, IQ1_M is 4.5 GB, IQ2_XXS is 5.1 GB, IQ2_XS is 5.7 GB, IQ2_S is 5.9 GB, IQ2_M is 6.4 GB and 15 more.
What context length does MixTAO-19B-pass support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download MixTAO-19B-pass GGUF?
The files are on Hugging Face in the mradermacher/MixTAO-19B-pass-i1-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 MixTAO-19B-pass 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 MixTAO-19B-pass on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations, which estimate 6.2 GB and 6.6 GB of VRAM at 8k context.
Does MixTAO-19B-pass support vision tasks?
No, the model does not include vision capabilities.
What license applies to MixTAO-19B-pass?
The model is released under the apache-2.0 license.