QW

Carnice MoE 35B A3B

QwenGGUF by samuelcardilloUpdated 2026-04-09
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant19.8 GB
Quick answer

Carnice MoE 35B A3B needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 19.8 GB (MXFP4_MOE) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Carnice MoE 35B A3B is a 34.7B-parameter Qwen model in GGUF format, quantized by samuelcardillo. Its trained context length is 256K tokens. The repository has 5 quant files, from 19.8 GB (MXFP4_MOE) to 36.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE19.8 GB 21.0 GB
Too big Get file →
Q4_K_M21.2 GB 22.3 GB
Too big Get file →
Q5_K_M24.7 GB 25.9 GB
Too big Get file →
Q6_K28.5 GB 29.7 GB
Too big Get file →
Q8_036.9 GB 38.1 GB
Too big Get file →

What GPU do you need for Carnice MoE 35B 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: 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: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).

Which Carnice MoE 35B A3B quant should you choose?

Q4_K_M is the usual starting point for Carnice MoE 35B A3B: it balances file size and quality well. Here it is a 21.2 GB file.

The Q8_0 file is 36.9 GB, about 1.7 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 MXFP4_MOE at 19.8 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bysamuelcardillo
FamilyQwen
Licenseapache-2.0
Downloads (HF)170
Last updated2026-04-09

Frequently asked questions about Carnice MoE 35B A3B

How much VRAM does Carnice MoE 35B A3B need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 Carnice MoE 35B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Carnice MoE 35B A3B GGUF?

It depends on the quant: MXFP4_MOE is 19.8 GB, Q4_K_M is 21.2 GB, Q5_K_M is 24.7 GB, Q6_K is 28.5 GB, Q8_0 is 36.9 GB.

What context length does Carnice MoE 35B 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 Carnice MoE 35B A3B GGUF?

The files are on Hugging Face in the samuelcardillo/Carnice-MoE-35B-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 Carnice MoE 35B 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.

Other GGUFs of Qwen3.5-35B-A3B

Similar models

Browse all →

More from samuelcardillo

All by samuelcardillo →

More Qwen models

All Qwen →

Other large models

All large models →