Instructions to use SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF 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 SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL
# Run inference directly in the terminal:
llama cli -hf SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL
# Run inference directly in the terminal:
llama cli -hf SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL

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 SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL
# Run inference directly in the terminal:
./llama-cli -hf SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL

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 SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL

Use Docker

docker model run hf.co/SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL

LM Studio
Jan
Ollama
How to use SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF with Ollama:
```
ollama run hf.co/SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL
```

Unsloth Studio

How to use SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF 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 SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF 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 SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF to start chatting

How to use SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL

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": "SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL

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 "SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL" \
  --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 SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL
```

Lemonade

How to use SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL

Run and chat with the model

lemonade run user.Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF-Q3_K_XL

List all available models

lemonade list

Hermes Agent

How to use SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL

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 SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF:Q3_K_XL

Run Hermes

hermes

Atomic Chat

Qwen3.5-122B-A10B-Opus-Reasoning — Dynamic imatrix GGUF + MTP draft

Custom GGUFs of timteh673/Qwen3.5-122B-A10B-Opus-Reasoning — an Opus-style reasoning fine-tune of Qwen3.5-122B-A10B (a Gated-DeltaNet hybrid MoE, arch qwen35moe). This repo improves on the upstream GGUFs in two independent ways:

Dynamic, importance-matrix (imatrix) quantization — an XL-tier per-tensor bit allocation that keeps the sensitive tensors high. The result is better quality-per-byte than stock K-quants. Similar recipe to unsloth (hat tip).
A multi-token-prediction (MTP) draft for speculative decoding — a lossless +33% throughput boost (the upstream GGUFs ship without an MTP head).

I built this quant to work well with my local AI workspace tool, Familiar. Familiar is an AI-enabled workspace where you can take Notes, collaborate in wikis, chat with models, and create smart automations with local models. This model performs well for most activities that Familiar needs. Check it out here:

https://github.com/sixvolts/familiar

Derivative work. Credit for the model goes to the upstream fine-tune author and the Qwen team; the MTP draft head is grafted from Unsloth's base-model MTP GGUF (see Credits).

Files

File	Size	bpw	Notes
`…-Q4_K_XL.gguf`	76.1 GB	4.99	Recommended. Near-lossless; beats standard Q4_K_M.
`…-Q3_K_XL.gguf`	60.2 GB	3.94	Smaller; ≈ standard-Q4_K_M quality at Q3 size.
`mtp-opus-q4kxl-draft.gguf`	3.36 GB	—	MTP speculative-decode draft (use with either quant via `-md`).
`opus-122b.imatrix`	0.34 GB	—	Importance matrix used (reproducibility).

1. Quality — perplexity (wikitext-2 test, 300 chunks @ 512 ctx, held-out)

Quant	PPL	Δ vs Q8_0
Q8_0 (reference)	4.8747	—
Q4_K_XL	4.8863	+0.24%
Q4_K_M (standard, for comparison)	4.9471	+1.49%
Q3_K_XL	4.9590	+1.73%

Q4_K_XL recovers ~84% of the Q4_K_M→Q8_0 quality gap for +1 GB; Q3_K_XL matches standard Q4_K_M quality at 10 GB smaller. All from the same Q8_0 source + same imatrix, so the deltas are clean.

Functional spot-check (both quants): correct on arithmetic (17×23=391), the bat-and-ball logic trap ($0.05), strict instruction-following, factual 2-sentence answers, and iterative-code generation. Reasoning traces are coherent.

2. Speed — MTP speculative decoding (lossless)

The model carries no MTP head in the upstream GGUF, so one was grafted from Unsloth's base MTP-GGUF. It transfers to this fine-tune extremely well (the tune barely shifted the trunk's hidden states), giving a real speedup. Speculative decoding is lossless — the target model verifies every drafted token, so output is identical to running the quant alone.

Config	tok/s	vs plain	Draft acceptance
Plain	46.8	—	—
MTP draft, `--spec-draft-n-max 2`	62.1	+32.7%	95.4%
MTP draft, `--spec-draft-n-max 3`	53.9	+15.2%	93.3%

n_max=2 is optimal here (a single nextn layer drafts ~2 tokens well; the 3rd costs more than it returns). Benchmarked on 4× MI100 (gfx908), one infinity fabric hive.

llama-server -m Qwen3.5-122B-A10B-Opus-Reasoning-Q4_K_XL.gguf \
             -md mtp-opus-q4kxl-draft.gguf \
             --spec-type draft-mtp -ngld 99 --spec-draft-n-max 2 \
             -ngl 99 -c 8192 -fa on --jinja

Note: always pass -c (the model's trained context is 262144; the default grabs it all and OOMs). Use a qwen35moe-capable llama.cpp (mainline supports it, incl. the GDN kernels).

Quantization recipe

imatrix from the standard calibration_datav3 corpus (512-token chunks).
Dynamic per-tensor types (llama-quantize --tensor-type-file):
- Q4_K_XL: bulk experts ffn_gate/up_exps=Q4_K; ffn_down_exps=Q5_K; embeddings, output, attention, GDN ssm_*, shared experts, first/last layers=Q6_K; GDN in-proj attn_qkv=Q5_K.
- Q3_K_XL: base Q3_K_M; experts Q3_K; ffn_down_exps/attn_qkv/first-last=Q4_K; shared experts=Q5_K; embeddings/output/attention/GDN-out=Q6_K.

Credits

Base model: Qwen/Qwen3.5-122B-A10B (Qwen team)
Fine-tune: timteh673/Qwen3.5-122B-A10B-Opus-Reasoning
MTP draft head grafted from: unsloth/Qwen3.5-122B-A10B-MTP-GGUF
Quantization, imatrix, and MTP graft: this repo. License follows the upstream model.