Instructions to use vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF",
	filename="Qwen3.5-122B-A10B-ROCmFP4-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 vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-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 vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF
# Run inference directly in the terminal:
llama cli -hf vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF
# Run inference directly in the terminal:
llama cli -hf vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

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 vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF
# Run inference directly in the terminal:
./llama-cli -hf vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

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 vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

Use Docker

docker model run hf.co/vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

LM Studio
Jan

vLLM

How to use vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

Ollama
How to use vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF with Ollama:
```
ollama run hf.co/vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF
```

Unsloth Studio

How to use vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-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 vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-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 vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF to start chatting

How to use vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

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": "vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-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 vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

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 vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

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 "vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF" \
  --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 vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF with Docker Model Runner:
```
docker model run hf.co/vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF
```

Lemonade

How to use vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

Run and chat with the model

lemonade run user.Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Qwen3.5 122B-A10B · ROCmFP4 iMatrix

The official Qwen checkpoint in a compact, importance-calibrated ROCmFP4 GGUF

122B total · 10B active · 60.70 GiB · 28.50 tok/s MTP-off · BF16 KLD 0.041366 · Decode 28.505 Decode speed + 36.89% faster Size - 13.47gb smaller

This GGUF uses custom ROCmFP4 tensor types. It requires ROCmFPX or a runtime with equivalent support. Stock llama.cpp, Ollama, LM Studio, and similar stock runtimes cannot load it.

This release was tested only on AMD Strix Halo / gfx1151. Other AMD targets may require a different ROCmFPX build and are untested; CPU-only, NVIDIA, and non-ROCmFPX runtimes are not supported by this card.

Downloads

Artifact	Direct download
Main iMatrix model — 60.70 GiB	Download `Qwen3.5-122B-A10B-ROCmFP4-iMatrix.gguf`
Optional MTP companion — 2.14 GiB	Download `Qwen3.5-122B-A10B-ROCmFP4-MTP.gguf`
Calibration matrix — 342.28 MiB	Download `Qwen3.5-122B-A10B-Bartowski.imatrix`

Browse every repository file →

What it is

This is an iMatrix-calibrated quantization of the official Qwen/Qwen3.5-122B-A10B checkpoint. It was built with ROCmFPX's compact Q4_0_ROCMFP4_STRIX_LEAN recipe; the hardware-oriented preset name is left out of the public filename.

	Result
BF16 mean KLD	0.041366 ± 0.002531
Greedy decode	28.505 tok/s
Sampled decode	28.485 tok/s
4,277-token prefill	356.900 tok/s

Files

File	Purpose	Size	SHA-256
`Qwen3.5-122B-A10B-ROCmFP4-iMatrix.gguf`	Main text model	65,184,265,120 bytes	`9f44eb8a8693f46af6e1b06f6219229eb074c1ec5527798e8a18d68034b381c8`
`Qwen3.5-122B-A10B-ROCmFP4-MTP.gguf`	Optional external MTP companion	2,294,290,272 bytes	`f59efaa7c184042a940df322d81921254b8e178d6eefc0fd5cdd7c5b0a9acbe3`
`Qwen3.5-122B-A10B-Bartowski.imatrix`	Calibration matrix	358,906,272 bytes	`e8bfa39dd663e70655035ad53bf715069b7f55175a8877a36bbbe18a0131fed6`
`chat_template.jinja`	Pinned Qwen3.5 chat template	7,756 bytes	`a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715`

The main model is complete and runs independently. The 23-tensor, one-layer MTP file is an optional external companion; no MTP layer is embedded in the main GGUF. Runtimes call this role a draft model, but Draft is omitted from the public filename because it does not mean unfinished.

Quality: stock and Heretic KLD

This is the card's only comparison between the stock and Heretic builds. Each ROCmFP4 iMatrix model was replayed against saved distributions from its own exact BF16 parent, using the same runtime, WikiText-2 token sequence, ROCm0 backend, two 512-token chunks, and 510 evaluated next-token distributions.

Build	Mean KLD from its BF16 parent
Stock iMatrix	0.041366 ± 0.002531
Heretic iMatrix	0.041395 ± 0.002697

Lower KLD means the quantized model's next-token distribution stayed closer to its own BF16 source. It does not rank the underlying stock and Heretic models, and it is not an intelligence or benchmark score.

The two-chunk scope is deliberately bounded: this is the demonstrated-safe BF16 workload on the tested 128 GB system. Treat it as a controlled calibration comparison, not a completed large-corpus acceptance gate. The Heretic card's headline uses a separate 11-chunk replay; its value is therefore not expected to match the two-chunk, method-matched figure reported here.

Performance

Measured on a 128 GB AMD Strix Halo system with Vulkan/RADV, 131,072 context, parallel 1, batch/ubatch 2048/1024, Q8_0 KV cache, flash attention, and MTP off. Values are medians from repeated runs of this stock artifact.

Workload	Prompt tokens	Repeats	Decode	Prompt processing
Greedy, 256 generated tokens	52	5	28.505 tok/s	71.934 tok/s
Sampled, 256 generated tokens	52	3	28.485 tok/s	70.957 tok/s
4,277-token prefill + 128 generated	4,277	3	28.107 tok/s	356.900 tok/s

These are single-system measurements, not general performance guarantees. The MTP companion is included for compatible runtimes, but this card does not claim an MTP speed result for the iMatrix artifact.

Quantization and matrix provenance

The model was quantized once from the validated BF16 GGUF using the Q4_0_ROCMFP4_STRIX_LEAN preset and the importance matrix published with bartowski/Qwen_Qwen3.5-122B-A10B-GGUF at revision f89fb67573c0155d8e5b6556204d86c75cdce0d8.

Tensor type	Count
`Q4_0_ROCMFP4_FAST`	457
`Q4_0_ROCMFP4`	60
`F32`	361
`Q5_K`	1

In this preset, attention K/V tensors retain dual-scale ROCmFP4 protection, most transformer weights use the compact FAST layout, and token embeddings use Q5_K while the separate output head uses the FAST layout. The artifact contains 879 tensors across 48 blocks and no embedded MTP layer.

The matrix contains 612 entries from 802 × 512-token chunks. Structural inspection found finite paired tensors and 37,323 of 37,332 expert count slots covered; nine slots had zero observations. A quantizer dry run accepted all 612 importance entries. The matrix publisher identified the official upstrQwen3-235B-A22Beam model but did not pin an immutable upstream weight revision, so that provenance limitation is recorded here rather than silently inferred.

Run

Use the ROCmFPX-built llama-server, not a stock llama.cpp binary:

llama-server \
  --model Qwen3.5-122B-A10B-ROCmFP4-iMatrix.gguf \
  --host 127.0.0.1 --port 8080 \
  -dev Vulkan0 --n-gpu-layers 999 \
  --ctx-size 131072 --parallel 1 \
  --flash-attn on --batch-size 2048 --ubatch-size 1024 \
  --cache-type-k q8_0 --cache-type-v q8_0 \
  --jinja --reasoning-format deepseek

Adjust context and cache settings for your memory budget. The tested runtime was charlie12345/ROCmFPX commit a6a93765f7ce9779c13f9881164a65f7a9f31198, built in Release mode for gfx1151 with Vulkan and HIP enabled. Correct inference also requires the duplicate Qwen3.5 MoE down-scale fix from llama.cpp PR #24331, commit 02810c7: without it, the expert down scale is applied twice. The pinned ROCmFPX commit did not yet contain the fix, so the tested runtime applied that exact nine-line correction locally; use a newer ROCmFPX revision or equivalent runtime that includes it. Results with other revisions have not yet been established.

The GGUF embeds the same chat template shipped separately in this repository, so the command uses --jinja without an external template path. --reasoning-format deepseek is the tested llama.cpp parser for this template's reasoning output, not a claim that the model is a DeepSeek derivative. The model file alone occupies 60.70 GiB; leave additional memory for the runtime and KV cache, especially at the tested 131,072-token context.

To enable the optional companion, append:

  --spec-type draft-mtp \
  --spec-draft-model Qwen3.5-122B-A10B-ROCmFP4-MTP.gguf \
  --spec-draft-device Vulkan0 --spec-draft-ngl 999 \
  --spec-draft-type-k f16 --spec-draft-type-v f16 \
  --spec-draft-n-max 2 --spec-draft-p-min 0.6 \
  --spec-draft-p-split 0.10 --spec-draft-backend-sampling

Tested system


Platform	AMD Strix Halo, 128 GB unified memory
GPU target	Radeon 8060S / `gfx1151`
Backend	Vulkan / RADV for serving; ROCm for bounded BF16 KLD collection
Kernel	Linux 6.17.0-1028-oem
Mesa	25.2.8

No vision projector is included; treat this release as text-only.

Lineage and credits

Official model and MTP tensors: Qwen/Qwen3.5-122B-A10B, revision dc4d348443bc740c68e2d77492492c11606384d5, Apache 2.0.
Importance matrix: bartowski/Qwen_Qwen3.5-122B-A10B-GGUF, revision f89fb67573c0155d8e5b6556204d86c75cdce0d8.
ROCmFP4 implementation, quantizer, and compatible runtime: charlie12345/ROCmFPX.
Strix Halo deployment stack: hec-ovi/llama-vulkan-strix.
Conversion, validation, benchmarking, and packaging: vmlinux.

Please preserve this lineage, the Apache 2.0 license, and a description of your changes when redistributing derivatives.

License

The distributed model derivative is provided under the upstream Apache License 2.0, whose text is included as LICENSE. Runtime and tooling repositories retain their own licenses. No runtime source code is bundled in this model repository.

Downloads last month: -

GGUF

Model size

122B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for vmlinux/Qwen3.5-122B-A10B-ROCmFP4-iMatrix-GGUF

Base model

Qwen/Qwen3.5-122B-A10B

Quantized

(130)

this model