ME

Hy Memory 30B A3B

MemoryGGUF by vinnipukhUpdated 2026-10-17
Download on Hugging Face
Parameters30B
Context256K
Layers48
Architecturehy_v3
Smallest quant0.2 GB
Quick answer

Hy Memory 30B A3B needs about 19.5 GB of memory at Q4_K_M (a 18.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 17 quants, from 0.2 GB to 60.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Hy Memory 30B A3B – a 30B long‑term memory writer for memory frameworks

Hy Memory 30B A3B is a 30B parameter model with ~3B active MoE parameters. It is designed to replace the general‑purpose LLM in memory frameworks such as Mem0, MemOS and Hy‑Memory, deciding what to store and how to update the memory bank. The model supports a 262K token context and is released under Apache‑2.0.

Good at

  • Long‑term memory writing
  • Memory bank management
  • Integration with Mem0 and MemOS

Limits

  • No vision support
  • Requires llama.cpp with hy_v3 support
  • Large VRAM needed for higher‑quality quants

Best for

  • Building persistent memory banks
  • Updating long‑term knowledge in applications
  • Memory‑centric LLM pipelines

Who it’s for. Developers building or extending memory‑centric LLM systems. The model is suitable for teams that need a dedicated writer to manage memory in frameworks like Mem0, MemOS, or Hy‑Memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 1.5 GB
Fits Get file →
Q1_04.4 GB 5.8 GB
Fits Get file →
TQ1_06.6 GB 7.9 GB
Tight Get file →
TQ2_08.0 GB 9.3 GB
Too big Get file →
Q2_08.7 GB 10.0 GB
Too big Get file →
Q3_K_M14.4 GB 15.8 GB
Too big Get file →
IQ4_XS16.1 GB 17.4 GB
Too big Get file →
Q4_017.0 GB 18.3 GB
Too big Get file →
Q4_K_M18.2 GB 19.5 GB
Too big Get file →
Q4_118.9 GB 20.2 GB
Too big Get file →
Q5_020.7 GB 22.1 GB
Too big Get file →
Q5_K_S20.7 GB 22.1 GB
Too big Get file →
Q5_K_M21.4 GB 22.7 GB
Too big Get file →
Q5_122.6 GB 23.9 GB
Too big Get file →
Q6_K24.7 GB 26.0 GB
Too big Get file →
Q8_032.0 GB 33.3 GB
Too big Get file →
BF1660.2 GB (2 parts) 61.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 17.02 GB, estimated 18.3 GB at 8 k context). For 12 GB VRAM, Q5_0 (20.75 GB, 22.1 GB). For 16 GB VRAM, Q6_K (24.71 GB, 26 GB). Higher‑quality quants such as Q8_0 or BF16 require more than 32 GB VRAM.

What GPU do you need for Hy Memory 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: the best quant that fits is the main file (0.2 GB file, about 1.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q1_0 (4.4 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is TQ1_0 (6.6 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q2_0 (8.7 GB file, about 10.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (14.4 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_1 (22.6 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (24.7 GB file, about 26.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (32.0 GB file, about 33.3 GB in use).

Which Hy Memory 30B A3B quant should you choose?

Q4_K_M is the usual starting point for Hy Memory 30B A3B: it balances file size and quality well. Here it is a 18.2 GB file.

The Q8_0 file is 32.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.2 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

Architecturehy_v3
Parameters30B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized byvinnipukh
FamilyMemory
Licenseapache-2.0
Downloads (HF)3,677
Last updated2026-10-17

Frequently asked questions about Hy Memory 30B A3B

How much VRAM does Hy Memory 30B A3B need?

About 19.5 GB at Q4_K_M with an 8K context window. That is the 18.2 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 Hy Memory 30B A3B on an 8 GB GPU?

Yes, with TQ1_0: the 6.6 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hy Memory 30B A3B GGUF?

It depends on the quant: file is 0.2 GB, Q1_0 is 4.4 GB, TQ1_0 is 6.6 GB, TQ2_0 is 8.0 GB, Q2_0 is 8.7 GB, Q3_K_M is 14.4 GB and 11 more.

What context length does Hy Memory 30B A3B 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 Hy Memory 30B A3B GGUF?

The files are on Hugging Face in the vinnipukh/Hy-Memory-30B-A3B-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 Hy Memory 30B A3B 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 Hy Memory 30B A3B on 8 GB VRAM?

Use the Q4_0 quant, which estimates 18.3 GB memory at 8 k context. It will fit on 8 GB VRAM with flash attention and careful batch sizing.

Does the model support vision or audio?

No. The model has no vision or audio capabilities; it is purely a text‑based memory writer.

What license applies to the GGUF files?

The GGUF files are released under Apache‑2.0, the same license as the original model.

Other GGUFs of Hy-Memory-30B-A3B

Similar models

Browse all →

More Memory models

All Memory →

Other medium models

All medium models →