QW

G Man 35B A3B abliterated mixed q2k MTP

QwopusGGUF by xero0000Updated 2026-07-02
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant18.7 GB
Quick answer

G Man 35B A3B abliterated mixed q2k MTP needs about 19.9 GB of memory at its main file (a 18.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

G Man 35B A3B abliterated mixed q2k MTP – a coding‑agent model with a transplanted MTP head

G Man 35B A3B abliterated mixed q2k MTP is a 35.5B‑parameter Qwen3.6‑35B‑A3B model fine‑tuned for agentic coding workflows. It uses a mixed‑quant layout and a grafted MTP head for speculative decoding. The model is released under Apache‑2.0 and is experimental.

Good at

  • coding agent workflows
  • tool calling and patching
  • low‑token waste execution

Limits

  • requires ~19.9 GB VRAM at 8 k context
  • no vision support
  • experimental safety status

Best for

  • local coding‑agent evaluation
  • tool‑driven debugging
  • agent harness integration

Who it’s for. Developers and researchers who need a local, token‑efficient coding agent. The model is suited for repeated tool decisions, patching, and test runs without long visible reasoning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—18.7 GB 19.9 GB
Too big Get file →

The only available GGUF file is the mixed‑quant version (~18.73 GB). It needs about 19.9 GB VRAM at 8 k context. For systems with 20 GB or more VRAM, this file is suitable. No other quantizations are provided.

What GPU do you need for G Man 35B A3B abliterated mixed q2k MTP?

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 the main file (18.7 GB file, about 19.9 GB in use).

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 byxero0000
FamilyQwopus
Licenseapache-2.0
Downloads (HF)63
Last updated2026-07-02

Frequently asked questions about G Man 35B A3B abliterated mixed q2k MTP

How much VRAM does G Man 35B A3B abliterated mixed q2k MTP need?

About 19.9 GB at its main file with an 8K context window. That is the 18.7 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 G Man 35B A3B abliterated mixed q2k MTP on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of G Man 35B A3B abliterated mixed q2k MTP GGUF?

It depends on the quant: file is 18.7 GB.

What context length does G Man 35B A3B abliterated mixed q2k MTP 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 G Man 35B A3B abliterated mixed q2k MTP GGUF?

The files are on Hugging Face in the xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does G Man 35B A3B abliterated mixed q2k MTP 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 this model on 8 GB VRAM?

No. The model requires approximately 19.9 GB VRAM at 8 k context.

Does this model support vision?

No, the model has no vision capabilities.

Is the model safe for production use?

It is an experimental community release intended for research and local evaluation.

Other GGUFs of Qwopus3.6-35B-A3B-Coder-MTP-GGUF

Similar models

Browse all →

More from xero0000

All by xero0000 →

More Qwopus models

All Qwopus →

Other large models

All large models →