OY

OYM Qimi 122B A10B K2.6

OymGGUF by mradermacherUpdated 2026-10-27
Download on Hugging Face
Parameters125B
Context256K
Layers49
Architectureqwen35moe
Smallest quant45.8 GB
Quick answer

OYM Qimi 122B A10B K2.6 needs about 77.2 GB of memory at Q4_K_M (a 75.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 9 quants, from 45.8 GB (Q2_K) to 88.7 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.

OYM Qimi 122B A10B K2.6 – a 122B multimodal Mixture‑of‑Experts model

OYM Qimi 122B A10B K2.6 is a 122B parameter multimodal Mixture‑of‑Experts model built on the Qwen35moe architecture. It includes a fully functional vision tower and a restored MTP head for speculative decoding. The model is completely decensored and preserves reasoning chains.

Good at

  • Multimodal vision and text
  • Reasoning with inline chains
  • Speculative decoding with MTP

Limits

  • Requires large VRAM for full precision
  • No explicit license restrictions listed
  • Vision support only, no other modalities

Best for

  • Vision‑enabled chatbots
  • Speculative decoding pipelines
  • Research on Mixture‑of‑Experts models

Who it’s for. Developers and researchers needing a large, multimodal LLM with preserved reasoning and speculative decoding capabilities. The model is suitable for applications that can accommodate its memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K45.8 GB 47.1 GB
Too big Get file →
Q3_K_S54.0 GB 55.3 GB
Too big Get file →
Q3_K_M59.8 GB 61.1 GB
Too big Get file →
Q3_K_L64.7 GB 66.0 GB
Too big Get file →
IQ4_XS67.6 GB 68.9 GB
Too big Get file →
Q4_K_S71.1 GB 72.4 GB
Too big Get file →
Q4_K_M75.8 GB 77.2 GB
Too big Get file →
Q5_K_S85.9 GB 87.3 GB
Too big Get file →
Q5_K_M88.7 GB 90.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (75.84 GB file, 77.2 GB memory at 8k context). For 16 GB VRAM, Q3_K_M (59.81 GB file, 61.1 GB memory) or Q4_K_S (71.08 GB file, 72.4 GB memory). Larger VRAM allows higher‑quality quants such as Q5_K_M (88.71 GB file, 90 GB memory).

What GPU do you need for OYM Qimi 122B A10B K2.6?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q2_K (45.8 GB file, about 47.1 GB in use).

Which OYM Qimi 122B A10B K2.6 quant should you choose?

Q4_K_M is the usual starting point for OYM Qimi 122B A10B K2.6: it balances file size and quality well. Here it is a 75.8 GB file.

If memory is tight, the smallest file is Q2_K at 45.8 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

Architectureqwen35moe
Parameters125B (approximate, mixture of experts)
Active parameters10B
Layers49
Trained context262,144 tokens
KV cache (fp16)98 KB per token

Source

Quantized bymradermacher
FamilyOym
Licenseother
Downloads (HF)1,637
Last updated2026-10-27

Frequently asked questions about OYM Qimi 122B A10B K2.6

How much VRAM does OYM Qimi 122B A10B K2.6 need?

About 77.2 GB at Q4_K_M with an 8K context window. That is the 75.8 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 OYM Qimi 122B A10B K2.6 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 47.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OYM Qimi 122B A10B K2.6 GGUF?

It depends on the quant: Q2_K is 45.8 GB, Q3_K_S is 54.0 GB, Q3_K_M is 59.8 GB, Q3_K_L is 64.7 GB, IQ4_XS is 67.6 GB, Q4_K_S is 71.1 GB and 3 more.

What context length does OYM Qimi 122B A10B K2.6 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 3.3 GB at 32K.

Where can I download OYM Qimi 122B A10B K2.6 GGUF?

The files are on Hugging Face in the mradermacher/OYM-Qimi-122B-A10B-K2.6-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 OYM Qimi 122B A10B K2.6 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 this model on 8 GB VRAM?

Use the Q4_K_M quant; it requires approximately 77.2 GB of VRAM at 8k context, which is beyond 8 GB, so it is not feasible.

Does the model support vision?

Yes, the vision tower is included and functional in all quant variants.

Is the model fully decensored?

The model is described as completely decensored across standard refusal axes.

Other GGUFs of OYM-Qimi-122B-A10B-K2.6

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Oym models

All Oym →

Other large models

All large models →