Boulesis v2 26B A4B needs about 25.8 GB of memory at Q4_K_M (a 17.2 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 10.8 GB (Q2_K) to 27.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Boulesis v2 26B A4B – Gemma4 MoE model with 26B parameters, 4B active experts
Boulesis v2 26B A4B is a Gemma4 architecture model with 26B parameters and 4B active experts. It was trained on 262144 context tokens and excels in reasoning, roleplay, and tool use. The model is a composite Gemma 4 RP model with a QK task arithmetic merge.
Good at
- reasoning
- roleplay
- tools
Limits
- Large memory requirement – 19.4 GB VRAM for Q2_K at 8 k context
- Requires 8 k context for memory estimates
- No vision support indicated
Best for
- Complex role‑play sessions with many characters
- Long‑form reasoning tasks
- Tool‑enabled conversational agents
Who it’s for. Developers and researchers building role‑playing assistants or reasoning bots that need a large MoE Gemma4 backbone. The model is suitable for applications that can allocate the necessary VRAM and support 8 k context length.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.8 GB | 19.4 GB | Too big | Get file → | |
| Q3_K_S | 12.5 GB | 21.1 GB | Too big | Get file → | |
| Q3_K_M | 13.6 GB | 22.2 GB | Too big | Get file → | |
| Q3_K_L | 14.1 GB | 22.7 GB | Too big | Get file → | |
| IQ4_XS | 14.5 GB | 23.0 GB | Too big | Get file → | |
| Q4_K_S | 15.9 GB | 24.4 GB | Too big | Get file → | |
| Q4_K_M | 17.2 GB | 25.8 GB | Too big | Get file → | |
| Q5_K_S | 18.5 GB | 27.0 GB | Too big | Get file → | |
| Q5_K_M | 19.6 GB | 28.2 GB | Too big | Get file → | |
| Q6_K | 23.2 GB | 31.8 GB | Too big | Get file → | |
| Q8_0 | 27.6 GB | 36.2 GB | Too big | Get file → |
For a 16 GB VRAM budget, Q4_K_S (15.88 GB file, 24.4 GB memory) is a practical choice. If 32 GB VRAM is available, Q6_K (23.24 GB file, 31.8 GB memory) offers higher quality. Smaller quants like Q2_K (10.82 GB file, 19.4 GB memory) are suitable only on very large GPUs.
What GPU do you need for Boulesis v2 26B A4B?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is IQ4_XS (14.5 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (23.2 GB file, about 31.8 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 Boulesis v2 26B A4B quant should you choose?
Q4_K_M is the usual starting point for Boulesis v2 26B A4B: it balances file size and quality well. Here it is a 17.2 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 Q2_K at 10.8 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 Boulesis v2 26B A4B
How much VRAM does Boulesis v2 26B A4B need?
About 25.8 GB at Q4_K_M with an 8K context window. That is the 17.2 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 Boulesis v2 26B A4B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Boulesis v2 26B A4B GGUF?
It depends on the quant: Q2_K is 10.8 GB, Q3_K_S is 12.5 GB, Q3_K_M is 13.6 GB, Q3_K_L is 14.1 GB, IQ4_XS is 14.5 GB, Q4_K_S is 15.9 GB and 5 more.
What context length does Boulesis v2 26B A4B 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 Boulesis v2 26B A4B GGUF?
The files are on Hugging Face in the mradermacher/Boulesis-v2-26B-A4B-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 Boulesis v2 26B A4B use?
Hugging Face lists the license as gemma. 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 Boulesis v2 26B A4B on 8 GB VRAM?
No. The smallest quant, Q2_K, requires 19.4 GB VRAM at 8 k context.
Does this model support vision?
Vision support is not indicated in the provided information.
What sampler settings are recommended?
Use temperature 1.0, top‑K 64, repetition penalty 1.05‑1.1, top‑P 0.95.