NE

Acereason-Nemotron-14B

NemotronGGUF by unslothUpdated 2025-05-23
Download on Hugging Face
Parameters14.8B
Context128K
Layers48
Architectureqwen2
Smallest quant3.8 GB
Quick answer

Acereason-Nemotron-14B needs about 11.1 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 3.8 GB (IQ1_S) to 29.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

AceReason-Nemotron-14B – a 14.8B Qwen2 model focused on math and code reasoning

AceReason-Nemotron-14B is a 14.8B parameter Qwen2 model trained entirely through reinforcement learning. It excels at mathematical problem solving and code reasoning tasks, with strong performance on AIME and LiveCodeBench benchmarks.

Good at

  • Math reasoning
  • Code reasoning
  • Step‑by‑step problem solving

Limits

  • Large VRAM requirement for higher‑quality quants
  • No vision support
  • License is other, not open source

Best for

  • Academic math tutoring
  • Programming interview prep
  • Automated code review

Who it’s for. Engineers and researchers needing a specialized reasoning model for math and code. The model is suitable for environments where reinforcement‑learned reasoning is valuable and sufficient GPU memory is available.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.8 GB 5.9 GB
Fits Get file →
IQ1_M4.0 GB 6.2 GB
Fits Get file →
IQ2_XXS4.5 GB 6.6 GB
Fits Get file →
IQ2_M5.4 GB 7.5 GB
Tight Get file →
Q2_K5.8 GB 7.9 GB
Tight Get file →
Q2_K_L6.0 GB 8.1 GB
Too big Get file →
IQ3_XXS6.0 GB 8.1 GB
Too big Get file →
Q2_K_XL6.1 GB 8.2 GB
Too big Get file →
Q3_K_S6.7 GB 8.8 GB
Too big Get file →
Q3_K_M7.3 GB 9.4 GB
Too big Get file →
Q3_K_XL7.6 GB 9.7 GB
Too big Get file →
IQ4_XS8.1 GB 10.3 GB
Too big Get file →
IQ4_NL8.5 GB 10.7 GB
Too big Get file →
Q4_K_S8.6 GB 10.7 GB
Too big Get file →
Q4_K_M9.0 GB 11.1 GB
Too big Get file →
Q4_K_XL9.1 GB 11.2 GB
Too big Get file →
Q4_19.4 GB 11.5 GB
Too big Get file →
Q5_K_S10.3 GB 12.4 GB
Too big Get file →
Q5_K_M10.5 GB 12.6 GB
Too big Get file →
Q5_K_XL10.5 GB 12.7 GB
Too big Get file →
Q6_K12.1 GB 14.2 GB
Too big Get file →
Q6_K_XL13.3 GB 15.4 GB
Too big Get file →
Q8_K_XL18.5 GB 20.7 GB
Too big Get file →
BF1629.5 GB 31.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (3.81 GB, 5.9 GB memory at 8 k context) or IQ1_M (4.04 GB, 6.2 GB). For 12 GB VRAM, Q4_K_M (8.99 GB, 11.1 GB) or Q5_K_S (10.27 GB, 12.4 GB) are suitable. For 24 GB VRAM, Q6_K (12.12 GB, 14.2 GB) or Q6_K_XL (13.27 GB, 15.4 GB) provide higher quality.

What GPU do you need for Acereason-Nemotron-14B?

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: the best quant that fits is IQ1_S (3.8 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q2_K (5.8 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (9.4 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K_XL (13.3 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_K_XL (18.5 GB file, about 20.7 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (29.5 GB file, about 31.7 GB in use).

Which Acereason-Nemotron-14B quant should you choose?

Q4_K_M is the usual starting point for Acereason-Nemotron-14B: it balances file size and quality well. Here it is a 9.0 GB file.

If memory is tight, the smallest file is IQ1_S at 3.8 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

Architectureqwen2
Parameters14.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)192 KB per token

Source

Quantized byunsloth
FamilyNemotron
Licenseother
Downloads (HF)1,340
Last updated2025-05-23

Frequently asked questions about Acereason-Nemotron-14B

How much VRAM does Acereason-Nemotron-14B need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.0 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 Acereason-Nemotron-14B on an 8 GB GPU?

Yes, with Q2_K: the 5.8 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 Acereason-Nemotron-14B GGUF?

It depends on the quant: IQ1_S is 3.8 GB, IQ1_M is 4.0 GB, IQ2_XXS is 4.5 GB, IQ2_M is 5.4 GB, Q2_K is 5.8 GB, Q2_K_L is 6.0 GB and 18 more.

What context length does Acereason-Nemotron-14B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Acereason-Nemotron-14B GGUF?

The files are on Hugging Face in the unsloth/AceReason-Nemotron-14B-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 Acereason-Nemotron-14B 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 AceReason-Nemotron-14B on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations, which fit within 8 GB VRAM and use about 6 GB of memory at 8 k context.

Does the model support image inputs?

No, the model has no vision capabilities and only processes text.

What license applies to this model?

The model is released under an "other" license, not an open source license.

Other GGUFs of AceReason-Nemotron-14B

Similar models

Browse all →

More from unsloth

All by unsloth →

More Nemotron models

All Nemotron →

Other medium models

All medium models →