NE

Apriel Nemotron 15b Thinker Magic_decensored_MPOA

NemotronGGUF by mradermacherUpdated 2026-02-08
Download on Hugging Face
Parameters15B
Context64K
Layers50
Architecturellama
Smallest quant0.0 GB
Quick answer

Apriel Nemotron 15b Thinker Magic_decensored_MPOA needs about 11.3 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 12.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.

15 billion‑parameter reasoning model with 65 k token context

Apriel Nemotron 15b Thinker Magic_decensored_MPOA is a 15 billion‑parameter llama architecture model trained for reasoning and tool use. It supports a 65536 token context window and is released under the MIT license.

Good at

  • Reasoning tasks
  • Tool invocation
  • Long‑context handling

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • No active parameters listed

Best for

  • Enterprise RAG
  • Academic reasoning
  • Agentic workflows

Who it’s for. Developers building reasoning‑heavy applications or academic researchers needing a large‑context model. The model is suitable for use in llama.cpp environments with GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.2 GB
Fits Get file →
IQ1_S3.6 GB 5.8 GB
Fits Get file →
IQ1_M3.9 GB 6.0 GB
Fits Get file →
IQ2_XXS4.3 GB 6.5 GB
Fits Get file →
IQ2_XS4.7 GB 6.9 GB
Fits Get file →
IQ2_S5.0 GB 7.2 GB
Fits Get file →
IQ2_M5.4 GB 7.5 GB
Tight Get file →
Q2_K_S5.4 GB 7.6 GB
Tight Get file →
Q2_K5.8 GB 8.0 GB
Tight Get file →
IQ3_XXS6.0 GB 8.2 GB
Too big Get file →
IQ3_XS6.4 GB 8.6 GB
Too big Get file →
Q3_K_S6.7 GB 8.9 GB
Too big Get file →
IQ3_S6.7 GB 8.9 GB
Too big Get file →
IQ3_M6.9 GB 9.1 GB
Too big Get file →
Q3_K_M7.4 GB 9.6 GB
Too big Get file →
Q3_K_L8.0 GB 10.2 GB
Too big Get file →
IQ4_XS8.2 GB 10.4 GB
Too big Get file →
Q4_08.6 GB 10.8 GB
Too big Get file →
IQ4_NL8.6 GB 10.8 GB
Too big Get file →
Q4_K_S8.7 GB 10.8 GB
Too big Get file →
Q4_K_M9.1 GB 11.3 GB
Too big Get file →
Q4_19.5 GB 11.7 GB
Too big Get file →
Q5_K_S10.4 GB 12.6 GB
Too big Get file →
Q5_K_M10.7 GB 12.8 GB
Too big Get file →
Q6_K12.3 GB 14.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 3.57 GB, memory 5.8 GB) or IQ1_M (3.85 GB, 6 GB). For 12 GB VRAM, IQ2_M (5.35 GB, 7.5 GB) or Q2_K (5.79 GB, 8 GB) are good choices. For 16 GB VRAM, Q3_K_M (7.4 GB, 9.6 GB) or Q4_K_M (9.11 GB, 11.3 GB) provide higher quality.

What GPU do you need for Apriel Nemotron 15b Thinker Magic_decensored_MPOA?

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: the best quant that fits is the main file (0.0 GB file, about 2.2 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ1_M (3.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q2_K (5.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (9.5 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 14.5 GB in use).

Which Apriel Nemotron 15b Thinker Magic_decensored_MPOA quant should you choose?

Q4_K_M is the usual starting point for Apriel Nemotron 15b Thinker Magic_decensored_MPOA: it balances file size and quality well. Here it is a 9.1 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters15B
Layers50
Trained context65,536 tokens
KV cache (fp16)200 KB per token

Frequently asked questions about Apriel Nemotron 15b Thinker Magic_decensored_MPOA

How much VRAM does Apriel Nemotron 15b Thinker Magic_decensored_MPOA need?

About 11.3 GB at Q4_K_M with an 8K context window. That is the 9.1 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 Apriel Nemotron 15b Thinker Magic_decensored_MPOA on an 8 GB GPU?

Yes, with Q2_K: the 5.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Apriel Nemotron 15b Thinker Magic_decensored_MPOA GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.6 GB, IQ1_M is 3.9 GB, IQ2_XXS is 4.3 GB, IQ2_XS is 4.7 GB, IQ2_S is 5.0 GB and 19 more.

What context length does Apriel Nemotron 15b Thinker Magic_decensored_MPOA support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.

Where can I download Apriel Nemotron 15b Thinker Magic_decensored_MPOA GGUF?

The files are on Hugging Face in the mradermacher/Apriel-Nemotron-15b-Thinker-Magic_decensored_MPOA-i1-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 Apriel Nemotron 15b Thinker Magic_decensored_MPOA use?

Hugging Face lists the license as mit. 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?

Yes, using the IQ1_S or IQ1_M quant files will fit within 8 GB VRAM with approximate memory usage of 5.8–6 GB at 8 k context.

Does the model support vision?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports a 65536 token context length.

Other GGUFs of Apriel-Nemotron-15b-Thinker-Magic_decensored_MPOA

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nemotron models

All Nemotron →

Other medium models

All medium models →