MA

MN 12B Mag Mell R1

MagGGUF by mradermacherUpdated 2024-09-17
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant4.8 GB
Quick answer

MN 12B Mag Mell R1 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 14 quants, from 4.8 GB (Q2_K) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

MN 12B Mag Mell R1 – a 12‑billion‑parameter llama model focused on reasoning

MN 12B Mag Mell R1 is a 12‑billion‑parameter llama model merged from six specialist models. It is optimized for reasoning tasks and general creative use. The model supports ChatML formatting and has been tested with temperature 1.25 and MinP 0.2 for stable outputs.

Good at

  • Reasoning
  • Creative worldbuilding
  • ChatML compatible

Limits

  • Large context size required
  • No vision support
  • License not specified

Best for

  • Complex reasoning queries
  • Creative fiction writing
  • ChatML‑based chatbots

Who it’s for. Developers and researchers needing a large llama model for reasoning and creative tasks. The model is suitable for local deployment using llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 6.6 GB
Fits Get file →
IQ3_XS5.3 GB 7.1 GB
Fits Get file →
Q3_K_S5.5 GB 7.4 GB
Tight Get file →
IQ3_S5.6 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_XS6.8 GB 8.6 GB
Too big Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 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 →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (7.48 GB file, ~9.3 GB VRAM). For 12 GB VRAM use Q5_K_M (8.73 GB file, ~10.6 GB VRAM). For 16 GB VRAM use Q6_K (10.06 GB file, ~11.9 GB VRAM). Estimates are approximate.

What GPU do you need for MN 12B Mag Mell R1?

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).

Which MN 12B Mag Mell R1 quant should you choose?

Q4_K_M is the usual starting point for MN 12B Mag Mell R1: 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 Q2_K at 4.8 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 bymradermacher
FamilyMag
Downloads (HF)25,051
Last updated2024-09-17

Frequently asked questions about MN 12B Mag Mell R1

How much VRAM does MN 12B Mag Mell R1 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 MN 12B Mag Mell R1 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 MN 12B Mag Mell R1 GGUF?

It depends on the quant: Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q3_K_S is 5.5 GB, IQ3_S is 5.6 GB, IQ3_M is 5.7 GB, Q3_K_M is 6.1 GB and 8 more.

What context length does MN 12B Mag Mell R1 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 MN 12B Mag Mell R1 GGUF?

The files are on Hugging Face in the mradermacher/MN-12B-Mag-Mell-R1-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 MN 12B Mag Mell R1 on 8 GB VRAM?

Use the Q4_K_M quant, which requires about 9.3 GB VRAM at 8K context. It is the smallest quant that fits within 8 GB with some headroom.

Does this model support image input?

No, MN 12B Mag Mell R1 does not have vision capabilities.

What sampler settings are recommended?

Use temperature 1.25 and MinP 0.2; avoid XTC and use DRY sparingly.

Other GGUFs of MN-12B-Mag-Mell-R1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mag models

All Mag →

Other medium models

All medium models →