MI

mirxa3.5 122B A10B

MirxaGGUF by mirxa2Updated 2026-03-28
Download on Hugging Face
Parameters122B
Context256K
Layers48
Architectureqwen35moe
Smallest quant39.9 GB
Quick answer

mirxa3.5 122B 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 13 quants, from 39.9 GB (IQ2_M) to 144.5 GB (Q8_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

mirxa3.5 122B A10B is a 122B-parameter Mirxa model in GGUF format, quantized by mirxa2. Its trained context length is 256K tokens. The repository has 13 quant files, from 39.9 GB (IQ2_M) to 144.5 GB (Q8_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M39.9 GB 41.2 GB
Too big Get file →
IQ3_XXS47.1 GB 48.5 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_K63.1 GB 64.4 GB
Too big Get file →
IQ4_XS65.2 GB 66.6 GB
Too big Get file →
Q4_K_M74.2 GB 75.5 GB
Too big Get file →
Q4_K78.7 GB 80.0 GB
Too big Get file →
Q5_K_M87.0 GB 88.3 GB
Too big Get file →
Q5_K93.5 GB 94.8 GB
Too big Get file →
Q6_K100.3 GB 101.6 GB
Too big Get file →
Q6_K104.6 GB 105.9 GB
Too big Get file →
Q8_K144.5 GB 145.8 GB
Too big Get file →

What GPU do you need for mirxa3.5 122B 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: 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 IQ2_M (39.9 GB file, about 41.2 GB in use).

Which mirxa3.5 122B A10B quant should you choose?

Q4_K_M is the usual starting point for mirxa3.5 122B A10B: it balances file size and quality well. Here it is a 74.2 GB file.

If memory is tight, the smallest file is IQ2_M at 39.9 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
Parameters122B (approximate, mixture of experts)
Active parameters10B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymirxa2
FamilyMirxa
Downloads (HF)93
Last updated2026-03-28

Frequently asked questions about mirxa3.5 122B A10B

How much VRAM does mirxa3.5 122B 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 mirxa3.5 122B A10B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 41.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mirxa3.5 122B A10B GGUF?

It depends on the quant: IQ2_M is 39.9 GB, IQ3_XXS is 47.1 GB, IQ3_M is 53.8 GB, Q3_K_M is 58.6 GB, Q3_K is 63.1 GB, IQ4_XS is 65.2 GB and 7 more.

What context length does mirxa3.5 122B 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 mirxa3.5 122B A10B GGUF?

The files are on Hugging Face in the mirxa2/mirxa3.5-122B-A10B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mirxa2

All by mirxa2 →

More Mirxa models

All Mirxa →

Other large models

All large models →