OP

OpenResearcher 30B A3B

OpenresearcherGGUF by mradermacherUpdated 2026-02-17
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant0.1 GB
Quick answer

OpenResearcher 30B A3B needs about 32.0 GB of memory at Q4_K_M (a 24.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.1 GB to 33.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

OpenResearcher 30B A3B – a 31.6B parameter agentic LLM for deep research

OpenResearcher 30B A3B is a 31.6B parameter model built on NVIDIA Nemotron architecture. It is fine‑tuned for long‑horizon research tasks and supports up to 1,048,576 context tokens. The model is released under the MIT license.

Good at

  • Long‑horizon research queries
  • Browser‑tool assisted reasoning
  • High accuracy on BrowseComp‑Plus

Limits

  • Requires large VRAM for full precision
  • No vision support
  • Limited to text only

Best for

  • Academic literature review
  • Complex data extraction
  • Multi‑step problem solving

Who it’s for. Researchers and developers needing a large, text‑only model capable of extended context. The model is suitable for applications that require deep reasoning over long documents.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 7.5 GB
Tight Get file →
IQ1_S17.9 GB 25.3 GB
Too big Get file →
IQ1_M17.9 GB 25.3 GB
Too big Get file →
IQ2_XXS17.9 GB 25.4 GB
Too big Get file →
IQ2_XS17.9 GB 25.4 GB
Too big Get file →
IQ2_S17.9 GB 25.4 GB
Too big Get file →
IQ2_M17.9 GB 25.4 GB
Too big Get file →
Q2_K17.9 GB 25.4 GB
Too big Get file →
IQ3_XXS17.9 GB 25.4 GB
Too big Get file →
IQ3_S17.9 GB 25.4 GB
Too big Get file →
IQ3_XS17.9 GB 25.4 GB
Too big Get file →
Q3_K_S17.9 GB 25.4 GB
Too big Get file →
IQ4_XS18.0 GB 25.4 GB
Too big Get file →
Q4_018.1 GB 25.5 GB
Too big Get file →
Q2_K_S18.1 GB 25.5 GB
Too big Get file →
IQ3_M18.1 GB 25.6 GB
Too big Get file →
Q3_K_M19.8 GB 27.3 GB
Too big Get file →
Q4_119.9 GB 27.4 GB
Too big Get file →
Q3_K_L20.7 GB 28.2 GB
Too big Get file →
Q4_K_S21.9 GB 29.4 GB
Too big Get file →
Q5_K_S23.8 GB 31.3 GB
Too big Get file →
Q4_K_M24.5 GB 32.0 GB
Too big Get file →
Q5_K_M26.0 GB 33.5 GB
Too big Get file →
Q6_K33.5 GB 41.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (≈25.3 GB memory at 8 k context). For 12 GB VRAM, IQ2_S or IQ2_M (≈25.4 GB). For 24 GB VRAM, Q4_K_M (≈32 GB) or Q5_K_M (≈33.5 GB). Memory estimates are approximate.

What GPU do you need for OpenResearcher 30B A3B?

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 the main file (0.1 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (24.5 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (33.5 GB file, about 41.0 GB in use).

Which OpenResearcher 30B A3B quant should you choose?

Q4_K_M is the usual starting point for OpenResearcher 30B A3B: it balances file size and quality well. Here it is a 24.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 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_moe
Parameters31.6B (approximate, mixture of experts)
Active parameters3B
Layers52
Trained context1,048,576 tokens
KV cache (fp16)832 KB per token

Source

Quantized bymradermacher
Licensemit
Downloads (HF)2,349
Last updated2026-02-17

Frequently asked questions about OpenResearcher 30B A3B

How much VRAM does OpenResearcher 30B A3B need?

About 32.0 GB at Q4_K_M with an 8K context window. That is the 24.5 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 OpenResearcher 30B A3B on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of OpenResearcher 30B A3B GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 17.9 GB, IQ1_M is 17.9 GB, IQ2_XXS is 17.9 GB, IQ2_XS is 17.9 GB, IQ2_S is 17.9 GB and 18 more.

What context length does OpenResearcher 30B A3B 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 7.0 GB at 8K and 27.9 GB at 32K.

Where can I download OpenResearcher 30B A3B GGUF?

The files are on Hugging Face in the mradermacher/OpenResearcher-30B-A3B-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 OpenResearcher 30B A3B 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 OpenResearcher 30B A3B on 8 GB VRAM?

No, the smallest quant requires about 25.3 GB memory at 8 k context. You would need at least 24 GB VRAM for Q4_K_M or higher.

Does the model support vision or image input?

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

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of OpenResearcher-30B-A3B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Openresearcher models

All Openresearcher →

Other medium models

All medium models →