OP

openNemo 9B abliterated

OpennemoGGUF by empero-aiUpdated 2026-03-23
Download on Hugging Face
Parameters8.89B
Context1024K
Layers56
Architecturenemotron_h
Smallest quant5.0 GB
Quick answer

openNemo 9B abliterated needs about 16.4 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 5.0 GB (Q2_K) to 17.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 37.6 GB.

openNemo 9B abliterated – a 9B‑parameter Nemotron‑H model without safety refusals

openNemo 9B abliterated is a 8.89‑billion‑parameter hybrid Mamba2 + sparse attention model. It was abliterated with Snakehead to remove safety refusal behavior while preserving coherence and reasoning. The model is available in multiple GGUF quantizations for llama.cpp and other tools.

Good at

  • Reasoning
  • Tool usage
  • Uncensored responses

Limits

  • No vision support
  • Large context size requires high VRAM
  • License is other

Best for

  • Research on safety alignment removal
  • Creative writing without filters
  • Applications needing unrestricted output

Who it’s for. Researchers and developers who need an uncensored version of Nemotron‑H for experimentation or applications where the user will implement their own filtering. The model is not suitable for general consumer use due to its lack of safety alignment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.0 GB 14.9 GB
Too big Get file →
Q3_K_S5.1 GB 15.0 GB
Too big Get file →
Q4_05.3 GB 15.2 GB
Too big Get file →
IQ4_XS5.4 GB 15.3 GB
Too big Get file →
Q3_K_M5.4 GB 15.3 GB
Too big Get file →
Q3_K_L5.5 GB 15.4 GB
Too big Get file →
Q4_K_S6.2 GB 16.1 GB
Too big Get file →
Q5_06.3 GB 16.2 GB
Too big Get file →
Q4_K_M6.5 GB 16.4 GB
Too big Get file →
Q5_K_S6.8 GB 16.7 GB
Too big Get file →
Q5_K_M7.1 GB 17.0 GB
Too big Get file →
Q6_K9.1 GB 19.0 GB
Too big Get file →
Q8_09.5 GB 19.4 GB
Too big Get file →
BF1617.8 GB 27.7 GB
Too big Get file →

For 6–8 GB VRAM, use Q4_K_M (file size 6.21 GB, ~16.1 GB memory at 8 k context). For 8–12 GB VRAM, Q5_K_M (6.78 GB, ~16.7 GB) or Q6_K (9.14 GB, ~19 GB). For high VRAM or quality priority, Q8_0 (9.46 GB, ~19.4 GB). The smallest files are Q2_K (5.01 GB, ~14.9 GB) and Q3_K_S (5.13 GB, ~15 GB) but may lose quality.

What GPU do you need for openNemo 9B abliterated?

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 Q3_K_L (5.5 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 19.4 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (17.8 GB file, about 27.7 GB in use).

Which openNemo 9B abliterated quant should you choose?

Q4_K_M is the usual starting point for openNemo 9B abliterated: it balances file size and quality well. Here it is a 6.5 GB file.

The Q8_0 file is 9.5 GB, about 1.4 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 5.0 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

Architecturenemotron_h
Parameters8.89B
Layers56
Trained context1,048,576 tokens
KV cache (fp16)1120 KB per token

Source

Quantized byempero-ai
FamilyOpennemo
Licenseother
Downloads (HF)856
Last updated2026-03-23

Frequently asked questions about openNemo 9B abliterated

How much VRAM does openNemo 9B abliterated need?

About 16.4 GB at Q4_K_M with an 8K context window. That is the 6.5 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 openNemo 9B abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of openNemo 9B abliterated GGUF?

It depends on the quant: Q2_K is 5.0 GB, Q3_K_S is 5.1 GB, Q4_0 is 5.3 GB, IQ4_XS is 5.4 GB, Q3_K_M is 5.4 GB, Q3_K_L is 5.5 GB and 8 more.

What context length does openNemo 9B abliterated support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 9.4 GB at 8K and 37.6 GB at 32K.

Where can I download openNemo 9B abliterated GGUF?

The files are on Hugging Face in the empero-ai/openNemo-9B-abliterated-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 openNemo 9B abliterated 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 openNemo 9B abliterated on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 16.1 GB memory at 8 k context, which fits in 8 GB VRAM when using 8 k context and efficient batching.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the NVIDIA Open Model License, the same as the base model.

Other GGUFs of openNemo-9B-abliterated

Similar models

Browse all →

More from empero-ai

All by empero-ai →

More Opennemo models

All Opennemo →

Other small models

All small models →