Instructions to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP",
	filename="Qwen3.6-35B-A3B-abliterated-mixed-q2k-MTP.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP
# Run inference directly in the terminal:
llama cli -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP
# Run inference directly in the terminal:
llama cli -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP
# Run inference directly in the terminal:
./llama-cli -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

Use Docker

docker model run hf.co/xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

LM Studio
Jan

vLLM

How to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

Ollama
How to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with Ollama:
```
ollama run hf.co/xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP
```

Unsloth Studio

How to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP to start chatting

How to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with Docker Model Runner:
```
docker model run hf.co/xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP
```

Lemonade

How to use xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull xero0000/G-Man-35B-A3B-abliterated-mixed-q2k-MTP

Run and chat with the model

lemonade run user.G-Man-35B-A3B-abliterated-mixed-q2k-MTP-{{QUANT_TAG}}

List all available models

lemonade list

G-Man-35B-A3B-abliterated-mixed-q2k-MTP / README.md

xero0000

Upload README.md with huggingface_hub

090da18 verified 1 day ago

preview code

Raw

History Blame Contribute Delete

4.76 kB

metadata

license: apache-2.0
base_model:
  - huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated
  - Jackrong/Qwopus3.6-35B-A3B-Coder-MTP-GGUF
base_model_relation: quantized
quantized_by: xero0000
pipeline_tag: text-generation
library_name: gguf
tags:
  - gguf
  - qwen35moe
  - moe
  - mixed-precision
  - imatrix
  - ik_llama.cpp
  - mtp
  - speculative-decoding
  - q2_k
  - uncensored
  - abliterated

🕴️ G-Man — Huihui Qwen3.6-35B-A3B abliterated Mixed q2_K + Transplanted MTP Head

Black Mesa mixed-quant series · operates outside the rules (uncensored) — and now arrives sooner.

The G-Man (plain mixed quant) mixed-precision GGUF of Huihui Qwen3.6-35B-A3B abliterated, with one addition: the multi-token-prediction (MTP) head from Qwopus-3.6-Coder surgically grafted on, enabling self-speculative decoding in ik_llama.cpp.

TL;DR: identical outputs to the plain mixed quant, but ~87 tok/s on code and ~83 tok/s on prose instead of ~78, on an 18 GB dual-GPU desktop. Free speed, verified token-by-token.

The head transplant

Huihui Qwen3.6-35B-A3B abliterated ships without an MTP head — but Qwopus-Coder is a fine-tune of the same Qwen3.6-35B-A3B base, and its blk.40 nextn head (a full extra layer: attention + MoE + eh_proj/enorm/hnorm glue, ~0.55 GB) predicts the next-next token from hidden states that this model's hidden space is a close sibling of. So we graft it:

append the donor's 20 blk.40.* tensors after the target's 40 layers,
bump block_count 40 → 41,
set qwen35moe.nextn_predict_layers = 1.

Why this is safe: speculative decoding verifies every drafted token against this model. A foreign head can never change the output distribution — a bad match only lowers the acceptance rate (= less speedup). Measured across the series, acceptance tracks fine-tune distance from the donor: base Qwen3.6 93/90 (code/prose t/s) > abliterated 87/83

Ornith 83/80 > AgentWorld 82/79, all against a 78 t/s no-MTP baseline.

Recipe

Quant layout (same as the parent mixed quant): ffn_*_exps on blocks 13–26 → Q2_K with importance matrix (the CPU-offloaded set); everything else Q4_K; output-class Q6_K. ~4.9 bpw effective, ~18.7 GB.
Head: blk.40 nextn/MTP layer from Qwopus-Coder mixed-q2k (Q4_K experts), grafted byte-exact.
The mixed layout exists because decode on CPU-offload rigs is RAM-bandwidth-bound: only the offloaded-layer bytes matter, so those get Q2_K while GPU-resident tensors keep Q4_K quality.

Measured performance

Rig: RTX 3060 Ti 8 GB + RTX 3080 10 GB, DDR4, ik_llama.cpp, 128K ctx, greedy.

workload	tok/s	vs 78 t/s no-MTP baseline
code generation	87	+12%
prose	83	+6%

How to run

Requires ik_llama.cpp — its -mtp flag is what drives the nextn head (mainline llama.cpp loads the file but ignores the head).

./llama-server -m Qwen3.6-35B-A3B-abliterated-mixed-q2k-MTP.gguf \
  --jinja --cache-type-k q4_0 --cache-type-v q4_0 --flash-attn on \
  --ctx-size 131072 --parallel 1 --n-gpu-layers 99 --ctx-checkpoints 8 \
  -ot 'blk\.(1[3-9]|2[0-9])\.ffn_(up|gate|down)_exps\.weight=CPU' \
  --tensor-split 44,56 --ubatch-size 256 \
  -mtp --ctx-size-draft 8192 \
  --no-mmap --threads 8 --no-warmup

Notes for 18 GB-class rigs:

The MTP draft context costs VRAM, which is why this profile runs 128K ctx (not 256K), a small 8K draft context, and pins expert layers 13–29 to CPU (three more than the plain mixed profile). With less freed VRAM, flash-attention temp allocations OOM mid-decode. More VRAM → pin fewer layers and/or raise ctx.
--ctx-checkpoints 8 caps ik's dynamically allocated SSM checkpoints (default 32 × 64 MiB ≈ 2 GB at deep context — an OOM trap on long agent sessions).
Add --reasoning off --reasoning-budget 0 for tool/browser loops (drop them for deep chat).
Drop -mtp (and the diet) and it behaves exactly like the parent mixed quant at 256K.

Credits

Base model: huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated (Apache-2.0)
MTP head donor: Jackrong/Qwopus3.6-35B-A3B-Coder-MTP-GGUF
Mixed quant, imatrix, transplant & profiling: xero0000
Series: Gordon (base) · Kleiner (coder) · G-Man (uncensored) · Vortigaunt (reasoner) · Alyx (agentic)