Pantheon Reasoning 26B A4B 1.1 needs about 26.0 GB of memory at Q4_K_M (a 17.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 27 quants, from 0.1 GB to 52.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Pantheon Reasoning 26B A4B 1.1 – a Gemma4 MoE model with reasoning and roleplay focus
Pantheon Reasoning 26B A4B 1.1 is a Gemma4 sparse MoE model with 26 billion parameters and 4 billion active parameters. It is trained on reasoning traces and roleplay data, providing reasoning and roleplay abilities. The model is released under the apache‑2.0 license.
Good at
- reasoning
- roleplay
- text adventure
Limits
- trained context 262144 tokens
- no vision support
- requires large VRAM for high‑quality quants
Best for
- interactive fiction generation
- character dialogue creation
- reasoning‑heavy prompts
Who it’s for. Developers and hobbyists who need a reasoning‑capable LLM for roleplay or interactive fiction. The model is suitable for users with access to sufficient GPU memory to run higher‑quality quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 8.6 GB | Too big | Get file → | |
| IQ2_XS | 10.4 GB | 18.9 GB | Too big | Get file → | |
| IQ2_S | 10.5 GB | 19.1 GB | Too big | Get file → | |
| IQ2_M | 11.0 GB | 19.6 GB | Too big | Get file → | |
| Q2_K | 11.2 GB | 19.7 GB | Too big | Get file → | |
| Q2_K_L | 11.9 GB | 20.5 GB | Too big | Get file → | |
| IQ3_XXS | 12.5 GB | 21.0 GB | Too big | Get file → | |
| IQ3_XS | 12.8 GB | 21.3 GB | Too big | Get file → | |
| Q3_K_S | 12.9 GB | 21.4 GB | Too big | Get file → | |
| Q3_K_M | 13.3 GB | 21.9 GB | Too big | Get file → | |
| Q3_K_L | 13.5 GB | 22.1 GB | Too big | Get file → | |
| IQ3_M | 13.6 GB | 22.2 GB | Too big | Get file → | |
| Q3_K_XL | 14.2 GB | 22.7 GB | Too big | Get file → | |
| IQ4_XS | 14.6 GB | 23.2 GB | Too big | Get file → | |
| IQ4_NL | 15.1 GB | 23.7 GB | Too big | Get file → | |
| Q4_0 | 15.2 GB | 23.7 GB | Too big | Get file → | |
| Q4_K_S | 16.3 GB | 24.8 GB | Too big | Get file → | |
| Q4_1 | 16.6 GB | 25.2 GB | Too big | Get file → | |
| Q4_K_M | 17.5 GB | 26.0 GB | Too big | Get file → | |
| Q4_K_L | 18.0 GB | 26.6 GB | Too big | Get file → | |
| Q5_K_S | 18.6 GB | 27.2 GB | Too big | Get file → | |
| Q5_K_M | 19.8 GB | 28.4 GB | Too big | Get file → | |
| Q5_K_L | 20.3 GB | 28.8 GB | Too big | Get file → | |
| Q6_K | 23.5 GB | 32.0 GB | Too big | Get file → | |
| Q6_K_L | 23.8 GB | 32.4 GB | Too big | Get file → | |
| Q8_0 | 27.6 GB | 36.2 GB | Too big | Get file → | |
| BF16 | 52.0 GB (2 parts) | 60.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XS or IQ2_S (file size 10.37 GB or 10.55 GB, memory ~18.9 GB or 19.1 GB). For 12 GB VRAM, IQ3_XS or Q3_K_S (file size 12.75 GB or 12.87 GB, memory ~21.3 GB or 21.4 GB). For 16 GB VRAM, Q4_K_S or Q4_1 (file size 16.26 GB or 16.61 GB, memory ~24.8 GB or 25.2 GB).
What GPU do you need for Pantheon Reasoning 26B A4B 1.1?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 8.6 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 8.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_0 (15.2 GB file, about 23.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (23.5 GB file, about 32.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (27.6 GB file, about 36.2 GB in use).
Which Pantheon Reasoning 26B A4B 1.1 quant should you choose?
Q4_K_M is the usual starting point for Pantheon Reasoning 26B A4B 1.1: it balances file size and quality well. Here it is a 17.5 GB file.
The Q8_0 file is 27.6 GB, about 1.6 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 the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Pantheon Reasoning 26B A4B 1.1
How much VRAM does Pantheon Reasoning 26B A4B 1.1 need?
About 26.0 GB at Q4_K_M with an 8K context window. That is the 17.5 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 Pantheon Reasoning 26B A4B 1.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Pantheon Reasoning 26B A4B 1.1 GGUF?
It depends on the quant: file is 0.1 GB, IQ2_XS is 10.4 GB, IQ2_S is 10.5 GB, IQ2_M is 11.0 GB, Q2_K is 11.2 GB, Q2_K_L is 11.9 GB and 21 more.
What context length does Pantheon Reasoning 26B A4B 1.1 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download Pantheon Reasoning 26B A4B 1.1 GGUF?
The files are on Hugging Face in the bartowski/Gryphe_Pantheon-Reasoning-26B-A4B-1.1-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 Pantheon Reasoning 26B A4B 1.1 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 this model on 8 GB VRAM?
Use IQ2_XS or IQ2_S quantizations; they require approximately 18.9 GB or 19.1 GB of VRAM at 8k context, which is close to 8 GB but may need swapping.
Does this model support vision?
No, the model does not have vision capabilities.
What is the maximum context length?
The model was trained with a context of 262144 tokens.