BE

Behemoth 128B v3

BehemothGGUF by bartowskiUpdated 2026-08-19
Download on Hugging Face
Parameters125B
Context256K
Layers88
Architecturellama
Smallest quant0.0 GB
Quick answer

Behemoth 128B v3 needs about 81.9 GB of memory at Q4_K_M (a 78.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 29 quants, from 0.0 GB to 250.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

128‑billion‑parameter llama model with 262k token context

Behemoth 128B v3 is a 128‑billion‑parameter llama model trained on 262,144 token context. It is released under Apache‑2.0 and supports only text input. The model is available in multiple quantizations via llama.cpp.

Good at

  • Large context handling
  • High‑capacity reasoning
  • Text‑only generation

Limits

  • No vision support
  • Large VRAM requirement for full precision
  • Requires recent llama.cpp release

Best for

  • Long‑form content creation
  • Complex question answering
  • Research prototyping

Who it’s for. Developers and researchers needing a large‑scale text model for experimentation. The model is suitable for those with sufficient GPU memory and familiarity with llama.cpp workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.5 GB
Fits Get file →
IQ1_S35.3 GB 38.8 GB
Too big Get file →
IQ1_M37.3 GB 40.7 GB
Too big Get file →
IQ2_XXS40.4 GB 43.9 GB
Too big Get file →
IQ2_XS43.4 GB 46.8 GB
Too big Get file →
IQ2_S46.1 GB 49.5 GB
Too big Get file →
IQ2_M48.6 GB 52.1 GB
Too big Get file →
Q2_K49.9 GB 53.3 GB
Too big Get file →
Q2_K_L51.4 GB 54.9 GB
Too big Get file →
IQ3_XXS52.2 GB 55.6 GB
Too big Get file →
IQ3_XS54.9 GB (2 parts) 58.4 GB
Too big Get file →
Q3_K_S57.0 GB (2 parts) 60.4 GB
Too big Get file →
IQ3_M59.5 GB (2 parts) 63.0 GB
Too big Get file →
Q3_K_M63.3 GB (2 parts) 66.7 GB
Too big Get file →
Q3_K_L67.0 GB (2 parts) 70.5 GB
Too big Get file →
Q3_K_XL68.4 GB (2 parts) 71.9 GB
Too big Get file →
IQ4_XS69.1 GB (2 parts) 72.6 GB
Too big Get file →
Q4_072.7 GB (2 parts) 76.2 GB
Too big Get file →
IQ4_NL72.8 GB (2 parts) 76.2 GB
Too big Get file →
Q4_K_S73.0 GB (2 parts) 76.5 GB
Too big Get file →
Q4_K_M78.4 GB (2 parts) 81.9 GB
Too big Get file →
Q4_K_L79.6 GB (2 parts) 83.1 GB
Too big Get file →
Q4_179.8 GB (2 parts) 83.2 GB
Too big Get file →
Q5_K_S87.1 GB (3 parts) 90.5 GB
Too big Get file →
Q5_K_M91.1 GB (3 parts) 94.6 GB
Too big Get file →
Q5_K_L92.1 GB (3 parts) 95.6 GB
Too big Get file →
Q6_K107.8 GB (3 parts) 111.3 GB
Too big Get file →
Q8_0132.9 GB (4 parts) 136.3 GB
Too big Get file →
BF16250.1 GB (7 parts) 253.5 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (78.41 GB file, ~81.9 GB memory at 8k context). For 16‑GB VRAM, Q4_K_L (79.6 GB file, ~83.1 GB memory). For 32‑GB VRAM, Q5_K_M (91.11 GB file, ~94.6 GB memory). File sizes and 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 the main file (0.0 GB file, about 3.5 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_XS (43.4 GB file, about 46.8 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 78.4 GB file.

The Q8_0 file is 132.9 GB, about 1.7 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 0.0 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

Architecturellama
Parameters125B
Layers88
Trained context262,144 tokens
KV cache (fp16)352 KB per token

Source

Quantized bybartowski
FamilyBehemoth
Licenseapache-2.0
Downloads (HF)9,070
Last updated2026-08-19

Frequently asked questions about Behemoth 128B v3

How much VRAM does Behemoth 128B v3 need?

About 81.9 GB at Q4_K_M with an 8K context window. That is the 78.4 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 35.3 GB, IQ1_M is 37.3 GB, IQ2_XXS is 40.4 GB, IQ2_XS is 43.4 GB, IQ2_S is 46.1 GB and 23 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 bartowski/TheDrummer_Behemoth-128B-v3-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?

No, the smallest quant requires at least 78 GB VRAM. Use a smaller model for 8 GB.

What license does the model use?

Apache‑2.0. The model can be used freely for commercial and non‑commercial purposes.

Does the model support image input?

No, it supports only text input.

Other GGUFs of Behemoth-128B-v3

Similar models

Browse all →

More from bartowski

All by bartowski →

More Behemoth models

All Behemoth →

Other large models

All large models →