HU

Huihui3.5 67B A3B

HuihuiGGUF by mradermacherUpdated 2026-07-29
Download on Hugging Face
Parameters66.9B
Context256K
Layers40
Architectureqwen35moe
Smallest quant0.4 GB
Quick answer

Huihui3.5 67B A3B needs about 41.9 GB of memory at Q4_K_M (a 40.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 24 quants, from 0.4 GB to 55.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Huihui3.5 67B A3B is a 66.9B-parameter Huihui model in GGUF format, quantized by mradermacher. Its trained context length is 256K tokens. The repository has 24 quant files, from 0.4 GB to 55.0 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.4 GB 1.6 GB
Fits Get file →
IQ1_S14.0 GB 15.1 GB
Too big Get file →
IQ1_M15.5 GB 16.6 GB
Too big Get file →
IQ2_XXS17.9 GB 19.1 GB
Too big Get file →
IQ2_XS19.9 GB 21.1 GB
Too big Get file →
IQ2_S20.2 GB 21.3 GB
Too big Get file →
IQ2_M22.1 GB 23.3 GB
Too big Get file →
Q2_K_S23.1 GB 24.3 GB
Too big Get file →
Q2_K24.7 GB 25.9 GB
Too big Get file →
IQ3_XXS26.0 GB 27.2 GB
Too big Get file →
IQ3_XS27.7 GB 28.8 GB
Too big Get file →
Q3_K_S29.1 GB 30.3 GB
Too big Get file →
IQ3_S29.2 GB 30.3 GB
Too big Get file →
IQ3_M29.5 GB 30.7 GB
Too big Get file →
Q3_K_M32.2 GB 33.4 GB
Too big Get file →
Q3_K_L34.8 GB 36.0 GB
Too big Get file →
IQ4_XS35.9 GB 37.1 GB
Too big Get file →
Q4_038.1 GB 39.3 GB
Too big Get file →
Q4_K_S38.3 GB 39.4 GB
Too big Get file →
Q4_K_M40.8 GB 41.9 GB
Too big Get file →
Q4_142.1 GB 43.2 GB
Too big Get file →
Q5_K_S46.2 GB 47.4 GB
Too big Get file →
Q5_K_M47.7 GB 48.8 GB
Too big Get file →
Q6_K55.0 GB 56.2 GB
Too big Get file →

What GPU do you need for Huihui3.5 67B 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 (0.4 GB file, about 1.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ1_S (14.0 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ2_M (22.1 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_M (29.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_S (46.2 GB file, about 47.4 GB in use).

Which Huihui3.5 67B A3B quant should you choose?

Q4_K_M is the usual starting point for Huihui3.5 67B A3B: it balances file size and quality well. Here it is a 40.8 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

Architectureqwen35moe
Parameters66.9B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymradermacher
FamilyHuihui
Licenseapache-2.0
Downloads (HF)156
Last updated2026-07-29

Frequently asked questions about Huihui3.5 67B A3B

How much VRAM does Huihui3.5 67B A3B need?

About 41.9 GB at Q4_K_M with an 8K context window. That is the 40.8 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 Huihui3.5 67B A3B on an 8 GB GPU?

Yes, with the smaller files: the 0.4 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Huihui3.5 67B A3B GGUF?

It depends on the quant: file is 0.4 GB, IQ1_S is 14.0 GB, IQ1_M is 15.5 GB, IQ2_XXS is 17.9 GB, IQ2_XS is 19.9 GB, IQ2_S is 20.2 GB and 18 more.

What context length does Huihui3.5 67B 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 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Huihui3.5 67B A3B GGUF?

The files are on Hugging Face in the mradermacher/Huihui3.5-67B-A3B-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 Huihui3.5 67B 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.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Huihui models

All Huihui →

Other large models

All large models →