OP

openNemo 9B

OpennemoGGUF by mradermacherUpdated 2026-03-24
Download on Hugging Face
Parameters8.89B
Context1024K
Layers56
Architecturenemotron_h
Smallest quant0.0 GB
Quick answer

openNemo 9B 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 25 quants, from 0.0 GB to 9.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 37.6 GB.

openNemo 9B – a 52‑layer hybrid Mamba‑Transformer model in GGUF format

openNemo 9B is a 52‑layer hybrid Mamba‑Transformer architecture based on NVIDIA’s Nemotron‑H. It is fully compatible with bitsandbytes quantization and QLoRA fine‑tuning on consumer GPUs. The model supports reasoning and tool‑use abilities.

Good at

  • Reasoning tasks
  • Tool‑use integration
  • Large context handling

Limits

  • No vision support
  • License type is other
  • Requires 8‑k context for estimates

Best for

  • Fine‑tuning with QLoRA
  • Running on consumer GPUs with bitsandbytes
  • Deploying in low‑latency inference setups

Who it’s for. Developers and researchers who need a hybrid Mamba‑Transformer model that can be quantized to 4‑bit or 8‑bit and fine‑tuned with QLoRA on a single GPU. The model is suitable for applications requiring large context and reasoning capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 9.9 GB
Too big Get file →
IQ1_S4.8 GB 14.7 GB
Too big Get file →
IQ1_M4.9 GB 14.8 GB
Too big Get file →
IQ2_XXS4.9 GB 14.8 GB
Too big Get file →
IQ2_XS4.9 GB 14.8 GB
Too big Get file →
IQ2_S5.0 GB 14.9 GB
Too big Get file →
IQ2_M5.0 GB 14.9 GB
Too big Get file →
Q2_K5.0 GB 14.9 GB
Too big Get file →
Q2_K_S5.1 GB 15.0 GB
Too big Get file →
IQ3_XXS5.1 GB 15.0 GB
Too big Get file →
IQ3_S5.1 GB 15.0 GB
Too big Get file →
IQ3_XS5.1 GB 15.0 GB
Too big Get file →
Q3_K_S5.1 GB 15.0 GB
Too big Get file →
IQ3_M5.2 GB 15.1 GB
Too big Get file →
IQ4_XS5.3 GB 15.2 GB
Too big Get file →
IQ4_NL5.3 GB 15.2 GB
Too big Get file →
Q4_05.3 GB 15.2 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_15.8 GB 15.7 GB
Too big Get file →
Q4_K_S6.2 GB 16.1 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 →

For 8‑GB VRAM, use IQ1_S (4.83 GB) or IQ1_M (4.85 GB). For 12‑GB VRAM, Q4_K_M (6.53 GB) or Q5_K_M (7.07 GB) are suitable. For 16‑GB VRAM, Q6_K (9.14 GB) provides the highest quality. Memory estimates are approximate.

What GPU do you need for openNemo 9B?

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: the best quant that fits is the main file (0.0 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (5.8 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (9.1 GB file, about 19.0 GB in use).

Which openNemo 9B quant should you choose?

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

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

Source

Quantized bymradermacher
FamilyOpennemo
Licenseother
Downloads (HF)621
Last updated2026-03-24

Frequently asked questions about openNemo 9B

How much VRAM does openNemo 9B 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of openNemo 9B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 4.8 GB, IQ1_M is 4.9 GB, IQ2_XXS is 4.9 GB, IQ2_XS is 4.9 GB, IQ2_S is 5.0 GB and 19 more.

What context length does openNemo 9B 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 GGUF?

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

Yes, using IQ1_S or IQ1_M quantizations, which are under 5 GB and require about 15 GB of RAM at 8k context.

Does openNemo 9B support vision tasks?

No, the model has no vision capabilities.

Is the model compatible with bitsandbytes quantization?

Yes, openNemo removes external CUDA kernels and is fully compatible with bitsandbytes 4‑bit and 8‑bit quantization.

Other GGUFs of openNemo-9B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Opennemo models

All Opennemo →

Other small models

All small models →