MA

Magnum 12b v2

MagnumGGUF by bartowskiUpdated 2024-08-06
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant4.4 GB
Quick answer

Magnum 12b v2 needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 20 quants, from 4.4 GB (IQ2_M) to 49.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Magnum 12b v2 – a 12‑billion parameter Llama‑style model fine‑tuned for Claude‑3‑style prose

Magnum 12b v2 is a 12‑billion parameter Llama architecture model fine‑tuned on Mistral‑Nemo‑Base‑2407. It is trained for 2 epochs on 8x NVIDIA H100 GPUs and uses ChatML prompting. The model is released under Apache‑2.0.

Good at

  • Claude‑3‑style prose generation
  • Instruct‑tuned ChatML interactions
  • Large context handling up to 1,024,000 tokens

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • License is Apache‑2.0

Best for

  • Chatbot development
  • Creative writing assistance
  • Long‑form content generation

Who it’s for. Developers building chat applications or content creation tools who need a high‑quality, open‑source LLM with large context capability. The model is suitable for users with sufficient GPU or system memory to run the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M4.4 GB 6.3 GB
Fits Get file →
Q2_K4.8 GB 6.6 GB
Fits Get file →
IQ3_XS5.3 GB 7.1 GB
Fits Get file →
Q2_K_L5.4 GB 7.3 GB
Tight Get file →
Q3_K_S5.5 GB 7.4 GB
Tight Get file →
IQ3_M5.7 GB 7.6 GB
Tight Get file →
Q3_K_M6.1 GB 7.9 GB
Tight Get file →
Q3_K_L6.6 GB 8.4 GB
Too big Get file →
IQ4_XS6.7 GB 8.6 GB
Too big Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q3_K_XL7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q4_K_L8.0 GB 9.8 GB
Too big Get file →
Q5_K_S8.5 GB 10.4 GB
Too big Get file →
Q5_K_M8.7 GB 10.6 GB
Too big Get file →
Q5_K_L9.1 GB 11.0 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q6_K_L10.4 GB 12.2 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →
F3249.0 GB 50.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (7 GB file, ~9 GB memory). For 12 GB VRAM, Q4_K_M (7.5 GB file, ~9.3 GB memory). For 16 GB VRAM, Q4_K_L (8 GB file, ~9.8 GB memory). Memory estimates are approximate.

What GPU do you need for Magnum 12b 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: the best quant that fits is Q3_K_M (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).

Which Magnum 12b v2 quant should you choose?

Q4_K_M is the usual starting point for Magnum 12b v2: it balances file size and quality well. Here it is a 7.5 GB file.

The Q8_0 file is 13.0 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 IQ2_M at 4.4 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
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized bybartowski
FamilyMagnum
Licenseapache-2.0
Downloads (HF)3,892
Last updated2024-08-06

Frequently asked questions about Magnum 12b v2

How much VRAM does Magnum 12b v2 need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Magnum 12b v2 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Magnum 12b v2 GGUF?

It depends on the quant: IQ2_M is 4.4 GB, Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q2_K_L is 5.4 GB, Q3_K_S is 5.5 GB, IQ3_M is 5.7 GB and 14 more.

What context length does Magnum 12b v2 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Magnum 12b v2 GGUF?

The files are on Hugging Face in the bartowski/magnum-12b-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 Magnum 12b v2 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 Magnum 12b v2 on 8 GB VRAM?

Yes, using the Q4_K_S quantization which requires about 9 GB of VRAM at 8k context.

What is the context length supported by this model?

The model was trained with a context of 1,024,000 tokens, but typical usage is 8k tokens for memory estimates.

Is this model open source?

It is released under the Apache‑2.0 license and can be downloaded from the Hugging Face repository.

Other GGUFs of magnum-v2-12b

Similar models

Browse all →

More from bartowski

All by bartowski →

More Magnum models

All Magnum →

Other medium models

All medium models →