MO

Monstral 123B v2

MonstralGGUF by bartowskiUpdated 2024-12-04
Download on Hugging Face
Parameters123B
Context128K
Layers88
Architecturellama
Smallest quant28.4 GB
Quick answer

Monstral 123B v2 needs about 76.7 GB of memory at Q4_K_M (a 73.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 22 quants, from 28.4 GB (IQ1_M) to 130.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

Monstral 123B v2 – a 123‑billion‑parameter LLM with tool‑use capability

Monstral 123B v2 is a 123‑billion‑parameter model built on the llama architecture. It merges Behemoth 1.2, Tess, and Magnum V4, providing a creative and colorful text generation experience. The model supports tool use and runs with llama.cpp.

Good at

  • Creative storytelling
  • Tool‑enabled interactions
  • Reduced repetition

Limits

  • No vision support
  • Large context requires high VRAM
  • License is other

Best for

  • Writing long narratives
  • Automated tool workflows
  • Content generation with low repetition

Who it’s for. Developers and writers who need a large, creative language model with tool‑use support. The model is suitable for applications that can accommodate its high VRAM and memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M28.4 GB 31.8 GB
Too big Get file →
IQ2_XXS32.4 GB 35.9 GB
Too big Get file →
IQ2_XS36.1 GB 39.5 GB
Too big Get file →
IQ2_M41.6 GB 45.1 GB
Too big Get file →
Q2_K45.2 GB 48.6 GB
Too big Get file →
Q2_K_L45.6 GB 49.0 GB
Too big Get file →
IQ3_XXS47.0 GB 50.5 GB
Too big Get file →
Q3_K_S52.8 GB (2 parts) 56.3 GB
Too big Get file →
IQ3_M55.3 GB (2 parts) 58.7 GB
Too big Get file →
Q3_K_M59.1 GB (2 parts) 62.6 GB
Too big Get file →
Q3_K_L64.6 GB (2 parts) 68.0 GB
Too big Get file →
Q3_K_XL64.9 GB (2 parts) 68.4 GB
Too big Get file →
IQ4_XS65.4 GB (2 parts) 68.9 GB
Too big Get file →
Q4_069.1 GB (2 parts) 72.5 GB
Too big Get file →
IQ4_NL69.2 GB (2 parts) 72.7 GB
Too big Get file →
Q4_069.3 GB (2 parts) 72.8 GB
Too big Get file →
Q4_K_S69.6 GB (2 parts) 73.0 GB
Too big Get file →
Q4_K_M73.2 GB (2 parts) 76.7 GB
Too big Get file →
Q5_K_S84.4 GB (3 parts) 87.8 GB
Too big Get file →
Q5_K_M86.5 GB (3 parts) 89.9 GB
Too big Get file →
Q6_K100.6 GB (3 parts) 104.0 GB
Too big Get file →
Q8_0130.3 GB (4 parts) 133.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (28.39 GB, 31.8 GB memory). For 16 GB VRAM, IQ2_XS (36.08 GB, 39.5 GB memory). For 24 GB VRAM, Q4_K_M (73.22 GB, 76.7 GB memory). Estimates are approximate.

What GPU do you need for Monstral 123B v2?

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: the best quant that fits is IQ1_M (28.4 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_M (41.6 GB file, about 45.1 GB in use).

Which Monstral 123B v2 quant should you choose?

Q4_K_M is the usual starting point for Monstral 123B v2: it balances file size and quality well. Here it is a 73.2 GB file.

The Q8_0 file is 130.3 GB, about 1.8 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 IQ1_M at 28.4 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

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

Source

Quantized bybartowski
FamilyMonstral
Licenseother
Downloads (HF)698
Last updated2024-12-04

Frequently asked questions about Monstral 123B v2

How much VRAM does Monstral 123B v2 need?

About 76.7 GB at Q4_K_M with an 8K context window. That is the 73.2 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 Monstral 123B v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 31.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Monstral 123B v2 GGUF?

It depends on the quant: IQ1_M is 28.4 GB, IQ2_XXS is 32.4 GB, IQ2_XS is 36.1 GB, IQ2_M is 41.6 GB, Q2_K is 45.2 GB, Q2_K_L is 45.6 GB and 16 more.

What context length does Monstral 123B v2 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 Monstral 123B v2 GGUF?

The files are on Hugging Face in the bartowski/Monstral-123B-v2-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 Monstral 123B v2 use?

Hugging Face lists the license as other. 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 Monstral 123B v2 on 8 GB VRAM?

Use the IQ1_M quant, which requires about 31.8 GB of VRAM at 8 k context. It will not fit on 8 GB VRAM.

Does the model support image inputs?

No, Monstral 123B v2 has no vision capability.

What is the context length of this model?

The trained context length is 131072 tokens.

Other GGUFs of Monstral-123B-v2

Similar models

Browse all →

More from bartowski

All by bartowski →

More Monstral models

All Monstral →

Other large models

All large models →