BE

Behemoth X 123B v2.2

BehemothGGUF by bartowskiUpdated 2026-10-07
Download on Hugging Face
Parameters123B
Context128K
Layers88
Architecturellama
Smallest quant0.1 GB
Quick answer

Behemoth X 123B v2.2 needs about 79.7 GB of memory at Q4_K_M (a 76.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 0.1 GB to 245.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

Behemoth X 123B v2.2 – a large llama‑based text model

Behemoth X 123B v2.2 is a 123B parameter llama model tuned by TheDrummer. It supports 131072 token context and is available in many llama.cpp quantizations. The model is text‑only and does not support vision.

Good at

  • Large context handling
  • High parameter count
  • Text generation

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License not specified

Best for

  • Long‑form content creation
  • Complex reasoning tasks
  • Large‑scale inference

Who it’s for. Developers and researchers needing a high‑capacity text model for inference on local hardware. Suitable for users with sufficient GPU memory to run the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 3.5 GB
Fits Get file →
IQ1_S27.3 GB 30.7 GB
Too big Get file →
IQ1_M30.9 GB 34.4 GB
Too big Get file →
IQ2_XXS35.6 GB 39.1 GB
Too big Get file →
IQ2_XS37.4 GB 40.8 GB
Too big Get file →
IQ2_S39.7 GB 43.2 GB
Too big Get file →
IQ2_M44.9 GB 48.3 GB
Too big Get file →
Q2_K46.4 GB 49.8 GB
Too big Get file →
IQ3_XXS51.6 GB 55.1 GB
Too big Get file →
Q3_K_S54.8 GB (2 parts) 58.2 GB
Too big Get file →
IQ3_XS55.4 GB (2 parts) 58.8 GB
Too big Get file →
Q3_K_M58.0 GB (2 parts) 61.4 GB
Too big Get file →
Q3_K_L61.3 GB (2 parts) 64.7 GB
Too big Get file →
IQ3_M65.2 GB (2 parts) 68.7 GB
Too big Get file →
IQ4_XS67.9 GB (2 parts) 71.4 GB
Too big Get file →
Q4_071.0 GB (2 parts) 74.5 GB
Too big Get file →
Q4_K_S71.8 GB (2 parts) 75.2 GB
Too big Get file →
IQ4_NL76.3 GB (2 parts) 79.7 GB
Too big Get file →
Q4_K_M76.3 GB (2 parts) 79.7 GB
Too big Get file →
Q4_178.0 GB (2 parts) 81.5 GB
Too big Get file →
Q4_K_L82.7 GB (3 parts) 86.2 GB
Too big Get file →
Q5_K_S87.2 GB (3 parts) 90.7 GB
Too big Get file →
Q5_K_M93.6 GB (3 parts) 97.0 GB
Too big Get file →
Q6_K_S103.1 GB (3 parts) 106.6 GB
Too big Get file →
Q6_K108.1 GB (3 parts) 111.5 GB
Too big Get file →
Q8_0130.3 GB (4 parts) 133.7 GB
Too big Get file →
BF16245.2 GB (7 parts) 248.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (76.27 GB file, ~79.7 GB memory). For 16 GB VRAM, use Q4_K_L (82.74 GB file, ~86.2 GB memory). For 32 GB VRAM, use Q5_K_M (93.59 GB file, ~97 GB memory).

What GPU do you need for Behemoth X 123B v2.2?

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 (0.1 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.5 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.5 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ1_S (27.3 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_S (39.7 GB file, about 43.2 GB in use).

Which Behemoth X 123B v2.2 quant should you choose?

Q4_K_M is the usual starting point for Behemoth X 123B v2.2: it balances file size and quality well. Here it is a 76.3 GB file.

The Q8_0 file is 130.3 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 0.1 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

Architecturellama
Parameters123B
Layers88
Trained context131,072 tokens
KV cache (fp16)352 KB per token

Source

Quantized bybartowski
FamilyBehemoth
Downloads (HF)3,704
Last updated2026-10-07

Frequently asked questions about Behemoth X 123B v2.2

How much VRAM does Behemoth X 123B v2.2 need?

About 79.7 GB at Q4_K_M with an 8K context window. That is the 76.3 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 X 123B v2.2 on an 8 GB GPU?

Yes, with the smaller files: the 0.1 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 X 123B v2.2 GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 27.3 GB, IQ1_M is 30.9 GB, IQ2_XXS is 35.6 GB, IQ2_XS is 37.4 GB, IQ2_S is 39.7 GB and 21 more.

What context length does Behemoth X 123B v2.2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 X 123B v2.2 GGUF?

The files are on Hugging Face in the bartowski/TheDrummer_Behemoth-X-123B-v2.2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Behemoth X 123B v2.2 on 8 GB VRAM?

Use the Q4_K_M quantization; it requires about 79.7 GB of VRAM at 8k context, so 8 GB is insufficient.

Does this model support image input?

No, the model only supports text input.

What is the maximum context length?

The model supports up to 131072 tokens.

Other GGUFs of Behemoth-X-123B-v2.2

Similar models

Browse all →

More from bartowski

All by bartowski →

More Behemoth models

All Behemoth →

Other large models

All large models →