Instructions to use AesSedai/Qwen3.5-397B-A17B-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 AesSedai/Qwen3.5-397B-A17B-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 AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M

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 AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M

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 AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use AesSedai/Qwen3.5-397B-A17B-GGUF with Ollama:
```
ollama run hf.co/AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use AesSedai/Qwen3.5-397B-A17B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AesSedai/Qwen3.5-397B-A17B-GGUF with Docker Model Runner:
```
docker model run hf.co/AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M
```

Lemonade

How to use AesSedai/Qwen3.5-397B-A17B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-397B-A17B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AesSedai/Qwen3.5-397B-A17B-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 AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M

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 AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AesSedai/Qwen3.5-397B-A17B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M

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 "AesSedai/Qwen3.5-397B-A17B-GGUF:Q4_K_M" \
  --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"

Offloading layers is not working for me

by tnuvkeg - opened Mar 24

Discussion

tnuvkeg

Mar 24

I can run Unsloth UD-Q4_K_XL (245gb) by offloading some layers to CPU with ik_llama (or llama.cpp) but no matter which layers I try to offload, I can't get IQ2_XS (132gb) to load because of memory issues.

Does the "new fused Up + Gate conversion" affects offloading in any way?

dehnhaide

Mar 24

Even if you engage with --"fit on"?

AesSedai

Owner Mar 24

•

edited Mar 24

Hi @tnuvkeg , have you pulled and compiled llama.cpp recently? There was a PR that just went in to fix mixed CPU + GPU offloading for the fused up + gate conversion: https://github.com/ggml-org/llama.cpp/pull/20910

tnuvkeg

Mar 26

•

edited Mar 26

Even if you engage with --"fit on"?

if in ik_llama I try with "--fit" I get "llama_model_load: error loading model: Manual tensor overrides cannot be used with --fit
"
("--fit on" I get "error: unknown argument: on")

in llama.cpp I get the same error about memory

tnuvkeg

Mar 26

Hi @tnuvkeg , have you pulled and compiled llama.cpp recently? There was a PR that just went in to fix mixed CPU + GPU offloading for the fused up + gate conversion: https://github.com/ggml-org/llama.cpp/pull/20910

Hi,
yes, I always keep both ik_llama and llama.cpp updated, just tried again with latest versions, and still the same... anyway, I guess it's only me, so no need to worry...

AesSedai

Owner Mar 26

Ah, ik_llama does not have the --fit flag. The fused up + gate is the same amount of weights overall but since that is fused into one tensor it is a bit tricker to get it to load onto the available space. The only PR I'm aware of is that 20910 I linked previously, but if you still have a problem in llama.cpp maybe open an issue with some of the logs from your server load? It sounds like another bug that may need fixing perhaps.

tnuvkeg

Mar 27

I need to look further into this, I could run big models just fine until yesterday where I updated ik_llama, then I needed to "downgrade" ik_llama to run the other models.
Although when I tried to run your IQ2_XS, I could load the Unsloth one just fine (and other big models like Kimi or Deepseek)... I'll keep an eye and try again...

AesSedai

Owner Mar 27

It might be related to how the layers are different sizes now? The bpw-selection algorithm from @eaddario can lead to uneven layer sizes and maybe that's causing some form of loading issue?

Using llama.cpp and the regular --fit worked for me since I loaded all of them to test PPL / KLD, so I think it might be a balancing issue of some kind perhaps?

dehnhaide

Mar 28

•

edited Mar 28

Ah, ik_llama does not have the --fit flag.

Actually it does... some dear developer at ik_llama (we all know very well) has blessed us with:
--fit-margin N --> safety margin in MiB when auto-fitting model offloading
--fit --> automatically determine which tensors to offload to the GPU(s)
Extra bonus, as per https://github.com/ikawrakow/ik_llama.cpp/pull/1540, now "-ts" based manual splits are honored

tnuvkeg

Apr 7

It might be related to how the layers are different sizes now? The bpw-selection algorithm from @eaddario can lead to uneven layer sizes and maybe that's causing some form of loading issue?

Using llama.cpp and the regular --fit worked for me since I loaded all of them to test PPL / KLD, so I think it might be a balancing issue of some kind perhaps?

Tried with --fit and didn't work also.

I guess the issue is with the "uneven layers", I do something like "-ot ".(6|7|8|9|[0-9][0-9]|[0-9][0-9][0-9]).ffn_(gate|up|down)_exps.=CPU"" and it works fine for bigger models/quants but not for this one.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment