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 14 quants, from 0.4 GB 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 multimodal Mixture‑of‑Experts model
OYM Qimi 122B A10B K2.6 is a 125 B parameter model with 10 B active experts. It supports text, vision, and MTP head for speculative decoding. The model is fully decensored and retains reasoning capabilities.
Good at
- Reasoning with inline chains
- Vision inference
- Speculative decoding with MTP
Limits
- Large context of 262144 tokens
- Requires high VRAM for full precision
- License is other, no public domain
Best for
- Complex reasoning tasks
- Multimodal content creation
- Speculative generation in low‑latency setups
Who it’s for. Developers building multimodal applications that need reasoning and vision. Researchers exploring Mixture‑of‑Experts architectures. Teams requiring a drop‑in replacement for Qwen3.5‑122B‑A10B with restored MTP head.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q2_K | 45.8 GB | 47.1 GB | Too big | Get file → | |
| Q3_K_S | 54.0 GB | 55.3 GB | Too big | Get file → | |
| IQ3_S | 54.2 GB | 55.5 GB | Too big | Get file → | |
| IQ3_M | 54.9 GB | 56.2 GB | Too big | Get file → | |
| Q3_K_M | 59.8 GB | 61.1 GB | Too big | Get file → | |
| Q3_K_L | 64.7 GB | 66.0 GB | Too big | Get file → | |
| IQ4_XS | 66.8 GB | 68.1 GB | Too big | Get file → | |
| Q4_0 | 70.8 GB | 72.1 GB | Too big | Get file → | |
| Q4_K_S | 71.1 GB | 72.4 GB | Too big | Get file → | |
| Q4_K_M | 75.8 GB | 77.2 GB | Too big | Get file → | |
| Q4_1 | 78.2 GB | 79.5 GB | Too big | Get file → | |
| Q5_K_S | 85.9 GB | 87.3 GB | Too big | Get file → | |
| Q5_K_M | 88.7 GB | 90.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (70.76 GB file, ~72.1 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (75.84 GB file, ~77.2 GB memory). For 32 GB VRAM, Q5_K_M (88.71 GB file, ~90 GB memory). Estimates are approximate.
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: 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 the main file (0.4 GB file, about 1.7 GB in use).
- 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 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
Source
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?
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 OYM Qimi 122B A10B K2.6 GGUF?
It depends on the quant: file is 0.4 GB, Q2_K is 45.8 GB, Q3_K_S is 54.0 GB, IQ3_S is 54.2 GB, IQ3_M is 54.9 GB, Q3_K_M is 59.8 GB and 8 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-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 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_0 quant, which requires about 72.1 GB memory at 8k context, so 8 GB VRAM is insufficient for full inference.
Does this model support vision?
Yes, the vision tower is included and functional.
Is the MTP head usable for speculative decoding?
Yes, the MTP head is restored and retrained for high draft‑token acceptance.