OR

Ornstein 122 A10B

OrnsteinGGUF by mradermacherUpdated 2026-05-23
Download on Hugging Face
Parameters122B
Context256K
Layers48
Architectureqwen35moe
Smallest quant0.4 GB
Quick answer

Ornstein 122 A10B needs about 75.5 GB of memory at Q4_K_M (a 74.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 0.4 GB to 86.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Ornstein 122 A10B – 122B parameter Qwen‑35MOE model

Ornstein 122 A10B is a 122 billion parameter Qwen‑35MOE model with 10 billion active experts. It supports reasoning and vision tasks and was trained on 262 144 context tokens. The model is released under the apache‑2.0 license.

Good at

  • Reasoning
  • Vision
  • Large context handling

Limits

  • No vision support in all quantizations
  • Requires large VRAM for full precision
  • Only available in GGUF format

Best for

  • Complex reasoning workflows
  • Vision‑enabled inference
  • Long‑form content generation

Who it’s for. Developers and researchers needing a large, mixture‑of‑experts model for reasoning and vision tasks. The model is suitable for environments that can accommodate its memory requirements and support GGUF loading via llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.4 GB 1.7 GB
Fits Get file →
IQ1_S25.3 GB 26.6 GB
Too big Get file →
IQ1_M28.1 GB 29.4 GB
Too big Get file →
IQ2_XXS32.6 GB 33.9 GB
Too big Get file →
IQ2_XS36.3 GB 37.6 GB
Too big Get file →
IQ2_S36.6 GB 37.9 GB
Too big Get file →
IQ2_M40.3 GB 41.6 GB
Too big Get file →
Q2_K_S42.1 GB 43.4 GB
Too big Get file →
Q2_K44.9 GB 46.2 GB
Too big Get file →
IQ3_XXS47.4 GB 48.7 GB
Too big Get file →
IQ3_XS50.3 GB 51.7 GB
Too big Get file →
Q3_K_S52.9 GB 54.2 GB
Too big Get file →
IQ3_S53.1 GB 54.4 GB
Too big Get file →
IQ3_M53.8 GB 55.1 GB
Too big Get file →
Q3_K_M58.6 GB 59.9 GB
Too big Get file →
Q3_K_L63.4 GB 64.7 GB
Too big Get file →
IQ4_XS65.5 GB 66.8 GB
Too big Get file →
Q4_069.3 GB 70.6 GB
Too big Get file →
Q4_K_S69.7 GB 71.0 GB
Too big Get file →
Q4_K_M74.2 GB 75.5 GB
Too big Get file →
Q4_176.6 GB 77.9 GB
Too big Get file →
Q5_K_S84.2 GB 85.5 GB
Too big Get file →
Q5_K_M86.9 GB 88.2 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (file size 25.34 GB, memory 26.6 GB). For 16 GB VRAM use IQ2_XS (file size 36.26 GB, memory 37.6 GB). For 32 GB VRAM use Q4_K_M (file size 74.21 GB, memory 75.5 GB). Estimates are approximate.

What GPU do you need for Ornstein 122 A10B?

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 (0.4 GB file, about 1.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ1_M (28.1 GB file, about 29.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q2_K (44.9 GB file, about 46.2 GB in use).

Which Ornstein 122 A10B quant should you choose?

Q4_K_M is the usual starting point for Ornstein 122 A10B: it balances file size and quality well. Here it is a 74.2 GB file.

If memory is tight, the smallest file is the first one in the table at 0.4 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

Architectureqwen35moe
Parameters122B (approximate, mixture of experts)
Active parameters10B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyOrnstein
Licenseapache-2.0
Downloads (HF)1,650
Last updated2026-05-23

Frequently asked questions about Ornstein 122 A10B

How much VRAM does Ornstein 122 A10B need?

About 75.5 GB at Q4_K_M with an 8K context window. That is the 74.2 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 Ornstein 122 A10B on an 8 GB GPU?

Yes, with the smaller files: the 0.4 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ornstein 122 A10B GGUF?

It depends on the quant: file is 0.4 GB, IQ1_S is 25.3 GB, IQ1_M is 28.1 GB, IQ2_XXS is 32.6 GB, IQ2_XS is 36.3 GB, IQ2_S is 36.6 GB and 17 more.

What context length does Ornstein 122 A10B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Ornstein 122 A10B GGUF?

The files are on Hugging Face in the mradermacher/Ornstein-122-A10B-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 Ornstein 122 A10B use?

Hugging Face lists the license as apache-2.0. 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 Ornstein 122 A10B on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 26.6 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does the model support vision tasks?

Yes, the model has detected vision ability, but no specific vision quantizations are listed.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ornstein models

All Ornstein →

Other large models

All large models →