AN

Anthracite Core_Magnum v4 22b R4

AnthraciteGGUF by anthracite-orgUpdated 2024-11-25
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant11.7 GB
Quick answer

Anthracite Core_Magnum v4 22b R4 needs about 15.7 GB of memory at Q4_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 11.7 GB (Q3_K_L) to 23.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Anthracite Core_Magnum v4 22b R4 – a 22.2B llama-based model

Anthracite Core_Magnum v4 22b R4 is a 22.2B parameter model fine‑tuned on Mistral‑Small‑Instruct‑2409. It is designed to emulate the prose quality of Claude 3 Sonnet and Opus. The model supports a 32,768 token context window.

Good at

  • High‑quality prose generation
  • Long‑form text completion
  • Instruction following

Limits

  • No vision support
  • License type is other
  • No mixture of experts

Best for

  • Creative writing
  • Technical documentation
  • Chatbot dialogue

Who it’s for. Developers and researchers who need a large language model with a long context window and a focus on high‑quality text generation. The model is suitable for applications requiring detailed, coherent responses over extended passages.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L11.7 GB 14.1 GB
Too big Get file →
Q4_K_M13.3 GB 15.7 GB
Too big Get file →
Q5_K_M15.7 GB 18.1 GB
Too big Get file →
Q6_K18.3 GB 20.6 GB
Too big Get file →
Q8_023.6 GB 26.0 GB
Too big Get file →

For 8 GB VRAM use Q3_K_L (file size 11.73 GB, estimated memory 14.1 GB). For 12 GB VRAM use Q4_K_M (13.34 GB, 15.7 GB). For 16 GB VRAM use Q5_K_M (15.72 GB, 18.1 GB). Higher quants require more memory.

What GPU do you need for Anthracite Core_Magnum v4 22b R4?

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: the best quant that fits is Q4_K_M (13.3 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 20.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (23.6 GB file, about 26.0 GB in use).

Which Anthracite Core_Magnum v4 22b R4 quant should you choose?

Q4_K_M is the usual starting point for Anthracite Core_Magnum v4 22b R4: it balances file size and quality well. Here it is a 13.3 GB file.

The Q8_0 file is 23.6 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 Q3_K_L at 11.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters22.2B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized byanthracite-org
Licenseother
Downloads (HF)1,114
Last updated2024-11-25

Frequently asked questions about Anthracite Core_Magnum v4 22b R4

How much VRAM does Anthracite Core_Magnum v4 22b R4 need?

About 15.7 GB at Q4_K_M with an 8K context window. That is the 13.3 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 Anthracite Core_Magnum v4 22b R4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Anthracite Core_Magnum v4 22b R4 GGUF?

It depends on the quant: Q3_K_L is 11.7 GB, Q4_K_M is 13.3 GB, Q5_K_M is 15.7 GB, Q6_K is 18.3 GB, Q8_0 is 23.6 GB.

What context length does Anthracite Core_Magnum v4 22b R4 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Anthracite Core_Magnum v4 22b R4 GGUF?

The files are on Hugging Face in the anthracite-org/magnum-v4-22b-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 Anthracite Core_Magnum v4 22b R4 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 this model on 8 GB VRAM?

Use the Q3_K_L quant. It requires about 14.1 GB of VRAM at 8k context, which is slightly above 8 GB, so it may need swapping or a smaller context.

Does this model support vision?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports a 32,768 token context window.

Similar models

Browse all →

More from anthracite-org

All by anthracite-org →

More Anthracite models

All Anthracite →

Other medium models

All medium models →