QW

Jackrong Qwopus3.6 35B A3B Coder ROCMFPX

QwopusGGUF by rcmoranoUpdated 2026-06-29
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant19.8 GB
Quick answer

Jackrong Qwopus3.6 35B A3B Coder ROCMFPX needs about 27.2 GB of memory at Q3_0 (a 26.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 8 quants, from 19.8 GB (Q3_0) to 37.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Jackrong Qwopus3.6 35B A3B Coder ROCMFPX is a 35.5B-parameter Qwopus model in GGUF format, quantized by rcmorano. Its trained context length is 256K tokens. The repository has 8 quant files, from 19.8 GB (Q3_0) to 37.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_019.8 GB 20.9 GB
Too big Get file →
Q4_020.2 GB 21.4 GB
Too big Get file →
Q4_023.3 GB 24.5 GB
Too big Get file →
Q3_026.0 GB 27.2 GB
Too big Get file →
Q6_029.4 GB 30.6 GB
Too big Get file →
Q6_033.1 GB 34.3 GB
Too big Get file →
Q8_036.7 GB 37.9 GB
Too big Get file →
Q8_037.3 GB 38.5 GB
Too big Get file →

What GPU do you need for Jackrong Qwopus3.6 35B A3B Coder ROCMFPX?

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_0 (20.2 GB file, about 21.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_0 (29.4 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.3 GB file, about 38.5 GB in use).

Which Jackrong Qwopus3.6 35B A3B Coder ROCMFPX quant should you choose?

Q3_0 (26.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q3_0 at 19.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters35.5B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized byrcmorano
FamilyQwopus
Licenseapache-2.0
Downloads (HF)345
Last updated2026-06-29

Frequently asked questions about Jackrong Qwopus3.6 35B A3B Coder ROCMFPX

How much VRAM does Jackrong Qwopus3.6 35B A3B Coder ROCMFPX need?

About 27.2 GB at Q3_0 with an 8K context window. That is the 26.0 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 Jackrong Qwopus3.6 35B A3B Coder ROCMFPX on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Jackrong Qwopus3.6 35B A3B Coder ROCMFPX GGUF?

It depends on the quant: Q3_0 is 19.8 GB, Q4_0 is 20.2 GB, Q4_0 is 23.3 GB, Q3_0 is 26.0 GB, Q6_0 is 29.4 GB, Q6_0 is 33.1 GB and 2 more.

What context length does Jackrong Qwopus3.6 35B A3B Coder ROCMFPX 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 2.8 GB at 32K.

Where can I download Jackrong Qwopus3.6 35B A3B Coder ROCMFPX GGUF?

The files are on Hugging Face in the rcmorano/Jackrong-Qwopus3.6-35B-A3B-Coder-ROCMFPX repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Jackrong Qwopus3.6 35B A3B Coder ROCMFPX 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 Qwopus3.6-35B-A3B-Coder

Similar models

Browse all →

More from rcmorano

All by rcmorano →

More Qwopus models

All Qwopus →

Other large models

All large models →