BlueBerry 3 needs about 89.0 GB of memory at Q4_K_M (a 87.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 9 quants, from 66.1 GB (Q3_K_S) to 93.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
BlueBerry 3 – 117B multilingual reasoning model
BlueBerry 3 is a 117B parameter model fine‑tuned from openai/gpt-oss-120b. It generates chain‑of‑thought reasoning in six languages: Farsi, English, Arabic, French, German, and Spanish. The model is licensed under Apache 2.0 and supports tool usage.
Good at
- Native multilingual reasoning
- Chain‑of‑thought generation
- Tool integration
Limits
- No vision support
- Large VRAM requirement
- Requires 8k context for memory estimates
Best for
- Multilingual QA
- Reasoning tasks in multiple languages
- Tool‑enabled applications
Who it’s for. Developers building multilingual reasoning systems or applications that require native chain‑of‑thought in multiple languages. The model is suitable for users with sufficient GPU memory to run the largest quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 66.1 GB | 67.3 GB | Too big | Get file → | |
| Q2_K | 66.2 GB | 67.3 GB | Too big | Get file → | |
| IQ4_XS | 67.0 GB | 68.1 GB | Too big | Get file → | |
| Q3_K_M | 71.1 GB | 72.2 GB | Too big | Get file → | |
| Q3_K_L | 73.4 GB | 74.5 GB | Too big | Get file → | |
| Q4_K_S | 80.9 GB | 82.0 GB | Too big | Get file → | |
| Q4_K_M | 87.9 GB | 89.0 GB | Too big | Get file → | |
| Q5_K_S | 88.0 GB | 89.1 GB | Too big | Get file → | |
| Q5_K_M | 93.9 GB | 95.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_S (66.15 GB file, ~67.3 GB memory at 8k context). For 16 GB VRAM, Q4_K_S (80.94 GB file, ~82 GB memory) or Q4_K_M (87.85 GB file, ~89 GB memory) are options. Larger models require more VRAM; memory estimates are approximate.
What GPU do you need for BlueBerry 3?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which BlueBerry 3 quant should you choose?
Q4_K_M is the usual starting point for BlueBerry 3: it balances file size and quality well. Here it is a 87.9 GB file.
If memory is tight, the smallest file is Q3_K_S at 66.1 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 BlueBerry 3
How much VRAM does BlueBerry 3 need?
About 89.0 GB at Q4_K_M with an 8K context window. That is the 87.9 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 BlueBerry 3 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 67.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of BlueBerry 3 GGUF?
It depends on the quant: Q3_K_S is 66.1 GB, Q2_K is 66.2 GB, IQ4_XS is 67.0 GB, Q3_K_M is 71.1 GB, Q3_K_L is 73.4 GB, Q4_K_S is 80.9 GB and 3 more.
What context length does BlueBerry 3 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 2.4 GB at 32K.
Where can I download BlueBerry 3 GGUF?
The files are on Hugging Face in the mradermacher/BlueBerry-3-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 BlueBerry 3 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 BlueBerry 3 on 8 GB VRAM?
The smallest quantization, Q3_K_S, requires about 67.3 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.
Does BlueBerry 3 support vision tasks?
No, the model does not include vision capabilities.
What license applies to BlueBerry 3?
The model is released under the Apache 2.0 license.