Behemoth 128B v3 needs about 78.3 GB of memory at Q4_K_M (a 74.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 0.0 GB to 88.3 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.
Behemoth 128B v3 – 125B llama model with large context and reasoning tools
Behemoth 128B v3 is a 125B parameter llama model trained on 262144 tokens. It supports reasoning and tool usage. The model is released under apache-2.0 and available in multiple GGUF quantizations.
Good at
- reasoning
- tool usage
- large context
Limits
- trained context 262144 tokens
- no vision support
- requires high VRAM for full precision
Best for
- complex reasoning tasks
- tool‑integrated workflows
- long‑form content generation
Who it’s for. Developers and researchers needing a large llama model with reasoning capabilities. The model is suitable for applications that can accommodate its memory footprint and do not require vision features.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.5 GB | Fits | Get file → | |
| IQ1_S | 27.2 GB | 30.6 GB | Too big | Get file → | |
| IQ1_M | 29.6 GB | 33.1 GB | Too big | Get file → | |
| IQ2_XXS | 33.7 GB | 37.1 GB | Too big | Get file → | |
| IQ2_XS | 37.3 GB | 40.8 GB | Too big | Get file → | |
| IQ2_S | 39.7 GB | 43.2 GB | Too big | Get file → | |
| IQ2_M | 43.0 GB | 46.4 GB | Too big | Get file → | |
| Q2_K_S | 43.0 GB | 46.5 GB | Too big | Get file → | |
| Q2_K | 46.6 GB | 50.0 GB | Too big | Get file → | |
| IQ3_XXS | 48.4 GB | 51.8 GB | Too big | Get file → | |
| IQ3_XS | 51.7 GB | 55.1 GB | Too big | Get file → | |
| Q3_K_S | 54.4 GB | 57.8 GB | Too big | Get file → | |
| IQ3_S | 54.5 GB | 58.0 GB | Too big | Get file → | |
| IQ3_M | 56.8 GB | 60.2 GB | Too big | Get file → | |
| Q3_K_M | 60.6 GB | 64.1 GB | Too big | Get file → | |
| Q3_K_L | 66.1 GB | 69.5 GB | Too big | Get file → | |
| IQ4_XS | 67.1 GB | 70.5 GB | Too big | Get file → | |
| Q4_0 | 71.0 GB | 74.5 GB | Too big | Get file → | |
| Q4_K_S | 71.2 GB | 74.7 GB | Too big | Get file → | |
| Q4_K_M | 74.9 GB | 78.3 GB | Too big | Get file → | |
| Q4_1 | 78.5 GB | 81.9 GB | Too big | Get file → | |
| Q5_K_S | 86.2 GB | 89.6 GB | Too big | Get file → | |
| Q5_K_M | 88.3 GB | 91.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (27.19 GB file, 30.6 GB memory at 8k context). For 16 GB VRAM, IQ2_XS (37.32 GB file, 40.8 GB memory) or Q2_K (46.59 GB file, 50 GB memory). For 24 GB VRAM, IQ3_S (54.51 GB file, 58 GB memory) or Q3_K_M (60.62 GB file, 64.1 GB memory). Memory estimates are approximate.
What GPU do you need for Behemoth 128B v3?
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 the main file (0.0 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 32 GB VRAM: the best quant that fits is IQ1_S (27.2 GB file, about 30.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q2_K_S (43.0 GB file, about 46.5 GB in use).
Which Behemoth 128B v3 quant should you choose?
Q4_K_M is the usual starting point for Behemoth 128B v3: it balances file size and quality well. Here it is a 74.9 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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 Behemoth 128B v3
How much VRAM does Behemoth 128B v3 need?
About 78.3 GB at Q4_K_M with an 8K context window. That is the 74.9 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 Behemoth 128B v3 on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Behemoth 128B v3 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 27.2 GB, IQ1_M is 29.6 GB, IQ2_XXS is 33.7 GB, IQ2_XS is 37.3 GB, IQ2_S is 39.7 GB and 17 more.
What context length does Behemoth 128B v3 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.
Where can I download Behemoth 128B v3 GGUF?
The files are on Hugging Face in the mradermacher/Behemoth-128B-v3-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 Behemoth 128B v3 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 Behemoth 128B v3 on 8 GB VRAM?
Only the smallest quant, IQ1_S, can be run with 8 GB VRAM, but it still requires about 30.6 GB memory at 8k context, so it is not feasible on 8 GB VRAM.
Does the model support vision?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.