LU

Lumimaid Magnum v4 12B

LumimaidGGUF by Undi95Updated 2024-12-22
Download on Hugging Face
Parameters12.2B
Context128K
Layers40
Architecturellama
Smallest quant7.5 GB
Quick answer

Lumimaid Magnum v4 12B 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 2 quants, from 7.5 GB (Q4_K_M) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Lumimaid Magnum v4 12B – a 12.2B‑parameter Llama model with 131072‑token context

Lumimaid Magnum v4 12B is a 12.2B‑parameter Llama model trained on a 131072‑token context. It supports tool usage and is available in two GGUF quantizations. The model is a merge of Lumimaid and Magnum with a Nemo finetune on Claude input.

Good at

  • Tool usage
  • Long context handling
  • 12B parameter scale

Limits

  • Large memory requirement
  • No vision support
  • License not specified

Best for

  • Tool‑enabled code generation
  • Long‑form document analysis
  • Chat with extended context

Who it’s for. Developers and researchers who need a large‑context Llama model with tool integration. The model is suitable for applications that require extended dialogue or document processing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →

For 8 GB VRAM use the Q4_K_M quant (file size 7.48 GB, estimated 9.3 GB memory at 8 k context). For 16 GB VRAM use Q8_0 (file size 13.02 GB, estimated 14.9 GB memory at 8 k context). These estimates are approximate.

What GPU do you need for Lumimaid Magnum v4 12B?

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: the best quant that fits is Q4_K_M (7.5 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).

Which Lumimaid Magnum v4 12B quant should you choose?

Q4_K_M is the usual starting point for Lumimaid Magnum v4 12B: 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.2B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byUndi95
FamilyLumimaid
Downloads (HF)399
Last updated2024-12-22

Frequently asked questions about Lumimaid Magnum v4 12B

How much VRAM does Lumimaid Magnum v4 12B 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 Lumimaid Magnum v4 12B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Lumimaid Magnum v4 12B GGUF?

It depends on the quant: Q4_K_M is 7.5 GB, Q8_0 is 13.0 GB.

What context length does Lumimaid Magnum v4 12B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Lumimaid Magnum v4 12B GGUF?

The files are on Hugging Face in the Undi95/Lumimaid-Magnum-v4-12B-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 Lumimaid Magnum v4 12B on 8 GB VRAM?

The Q4_K_M quant uses about 9.3 GB memory at 8 k context, so 8 GB VRAM is insufficient. A lower context or a different quant would be required.

Does this model support vision?

No vision support is provided for Lumimaid Magnum v4 12B.

What is the context length of this model?

The model was trained with a 131072‑token context length.

Other GGUFs of Lumimaid-v0.2-12B

Similar models

Browse all →

More from Undi95

All by Undi95 →

More Lumimaid models

All Lumimaid →

Other medium models

All medium models →