Instructions to use ubergarm/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 ubergarm/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 ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

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 ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

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 ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Use Docker

docker model run hf.co/ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use ubergarm/Qwen3.5-397B-A17B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubergarm/Qwen3.5-397B-A17B-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": "ubergarm/Qwen3.5-397B-A17B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Ollama
How to use ubergarm/Qwen3.5-397B-A17B-GGUF with Ollama:
```
ollama run hf.co/ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
```
Unsloth Desktop

How to use ubergarm/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 ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

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": "ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ubergarm/Qwen3.5-397B-A17B-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Run and chat with the model

lemonade run user.Qwen3.5-397B-A17B-GGUF-Q2_K

List all available models

lemonade list

Hermes Agent

How to use ubergarm/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 ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

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 ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ubergarm/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 ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

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 "ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K" \
  --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"

Some lm-evaluation-harness results for smol-IQ2_XS

by tarruda - opened Feb 24

Discussion

tarruda

Feb 24

Results are pretty good so far:

|                 Tasks                 |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|---------------------------------------|------:|------|-----:|------|---|-----:|---|-----:|
|mmlu                                   |      2|none  |      |acc   |   |0.8786|±  |0.0026|
| - humanities                          |      2|none  |     0|acc   |↑  |0.8162|±  |0.0054|
|  - formal_logic                       |      1|none  |     0|acc   |↑  |0.7778|±  |0.0372|
|  - high_school_european_history       |      1|none  |     0|acc   |↑  |0.9091|±  |0.0224|
|  - high_school_us_history             |      1|none  |     0|acc   |↑  |0.9559|±  |0.0144|
|  - high_school_world_history          |      1|none  |     0|acc   |↑  |0.9620|±  |0.0124|
|  - international_law                  |      1|none  |     0|acc   |↑  |0.9421|±  |0.0213|
|  - jurisprudence                      |      1|none  |     0|acc   |↑  |0.9074|±  |0.0280|
|  - logical_fallacies                  |      1|none  |     0|acc   |↑  |0.9325|±  |0.0197|
|  - moral_disputes                     |      1|none  |     0|acc   |↑  |0.8902|±  |0.0168|
|  - moral_scenarios                    |      1|none  |     0|acc   |↑  |0.6715|±  |0.0157|
|  - philosophy                         |      1|none  |     0|acc   |↑  |0.9100|±  |0.0163|
|  - prehistory                         |      1|none  |     0|acc   |↑  |0.9383|±  |0.0134|
|  - professional_law                   |      1|none  |     0|acc   |↑  |0.7497|±  |0.0111|
|  - world_religions                    |      1|none  |     0|acc   |↑  |0.9298|±  |0.0196|
| - other                               |      2|none  |     0|acc   |↑  |0.9070|±  |0.0049|
|  - business_ethics                    |      1|none  |     0|acc   |↑  |0.8600|±  |0.0349|
|  - clinical_knowledge                 |      1|none  |     0|acc   |↑  |0.9358|±  |0.0151|
|  - college_medicine                   |      1|none  |     0|acc   |↑  |0.8902|±  |0.0238|
|  - global_facts                       |      1|none  |     0|acc   |↑  |0.7400|±  |0.0441|
|  - human_aging                        |      1|none  |     0|acc   |↑  |0.8655|±  |0.0229|
|  - management                         |      1|none  |     0|acc   |↑  |0.9126|±  |0.0280|
|  - marketing                          |      1|none  |     0|acc   |↑  |0.9658|±  |0.0119|
|  - medical_genetics                   |      1|none  |     0|acc   |↑  |1.0000|±  |0.0000|
|  - miscellaneous                      |      1|none  |     0|acc   |↑  |0.9681|±  |0.0063|
|  - nutrition                          |      1|none  |     0|acc   |↑  |0.9314|±  |0.0145|
|  - professional_accounting            |      1|none  |     0|acc   |↑  |0.8652|±  |0.0204|
|  - professional_medicine              |      1|none  |     0|acc   |↑  |0.9632|±  |0.0114|
|  - virology                           |      1|none  |     0|acc   |↑  |0.5663|±  |0.0386|
| - social sciences                     |      2|none  |     0|acc   |↑  |0.9314|±  |0.0045|
|  - econometrics                       |      1|none  |     0|acc   |↑  |0.8246|±  |0.0358|
|  - high_school_geography              |      1|none  |     0|acc   |↑  |0.9495|±  |0.0156|
|  - high_school_government_and_politics|      1|none  |     0|acc   |↑  |0.9896|±  |0.0073|
|  - high_school_macroeconomics         |      1|none  |     0|acc   |↑  |0.9462|±  |0.0114|
|  - high_school_microeconomics         |      1|none  |     0|acc   |↑  |0.9748|±  |0.0102|
|  - high_school_psychology             |      1|none  |     0|acc   |↑  |0.9706|±  |0.0072|
|  - human_sexuality                    |      1|none  |     0|acc   |↑  |0.9237|±  |0.0233|
|  - professional_psychology            |      1|none  |     0|acc   |↑  |0.9069|±  |0.0118|
|  - public_relations                   |      1|none  |     0|acc   |↑  |0.8182|±  |0.0369|
|  - security_studies                   |      1|none  |     0|acc   |↑  |0.8816|±  |0.0207|
|  - sociology                          |      1|none  |     0|acc   |↑  |0.9154|±  |0.0197|
|  - us_foreign_policy                  |      1|none  |     0|acc   |↑  |0.9700|±  |0.0171|
| - stem                                |      2|none  |     0|acc   |↑  |0.8925|±  |0.0054|
|  - abstract_algebra                   |      1|none  |     0|acc   |↑  |0.7600|±  |0.0429|
|  - anatomy                            |      1|none  |     0|acc   |↑  |0.8667|±  |0.0294|
|  - astronomy                          |      1|none  |     0|acc   |↑  |0.9671|±  |0.0145|
|  - college_biology                    |      1|none  |     0|acc   |↑  |0.9653|±  |0.0153|
|  - college_chemistry                  |      1|none  |     0|acc   |↑  |0.7000|±  |0.0461|
|  - college_computer_science           |      1|none  |     0|acc   |↑  |0.9000|±  |0.0302|
|  - college_mathematics                |      1|none  |     0|acc   |↑  |0.8300|±  |0.0378|
|  - college_physics                    |      1|none  |     0|acc   |↑  |0.8725|±  |0.0332|
|  - computer_security                  |      1|none  |     0|acc   |↑  |0.9000|±  |0.0302|
|  - conceptual_physics                 |      1|none  |     0|acc   |↑  |0.9234|±  |0.0174|
|  - electrical_engineering             |      1|none  |     0|acc   |↑  |0.9172|±  |0.0230|
|  - elementary_mathematics             |      1|none  |     0|acc   |↑  |0.9418|±  |0.0121|
|  - high_school_biology                |      1|none  |     0|acc   |↑  |0.9710|±  |0.0096|
|  - high_school_chemistry              |      1|none  |     0|acc   |↑  |0.8719|±  |0.0235|
|  - high_school_computer_science       |      1|none  |     0|acc   |↑  |0.9200|±  |0.0273|
|  - high_school_mathematics            |      1|none  |     0|acc   |↑  |0.7815|±  |0.0252|
|  - high_school_physics                |      1|none  |     0|acc   |↑  |0.9073|±  |0.0237|
|  - high_school_statistics             |      1|none  |     0|acc   |↑  |0.8889|±  |0.0214|
|  - machine_learning                   |      1|none  |     0|acc   |↑  |0.8661|±  |0.0323|

|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|-----:|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |   |0.8786|±  |0.0026|
| - humanities     |      2|none  |     0|acc   |↑  |0.8162|±  |0.0054|
| - other          |      2|none  |     0|acc   |↑  |0.9070|±  |0.0049|
| - social sciences|      2|none  |     0|acc   |↑  |0.9314|±  |0.0045|
| - stem           |      2|none  |     0|acc   |↑  |0.8925|±  |0.0054|

|        Tasks        |Version|Filter|n-shot| Metric |   |Value |   |Stderr|
|---------------------|------:|------|-----:|--------|---|-----:|---|-----:|
|gpqa_diamond_zeroshot|      1|none  |     0|acc     |↑  |0.5202|±  |0.0356|
|                     |       |none  |     0|acc_norm|↑  |0.5202|±  |0.0356|

|          Tasks          |Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-------------------------|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gpqa_diamond_cot_zeroshot|      1|flexible-extract|     0|exact_match|↑  |0.8232|±  |0.0272|
|                         |       |strict-match    |     0|exact_match|↑  |0.8232|±  |0.0272|

|  Tasks  |Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|---------|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k_cot|      3|flexible-extract|     8|exact_match|↑  |0.8810|±  |0.0089|
|         |       |strict-match    |     8|exact_match|↑  |0.8643|±  |0.0094|

|Tasks |Version|Filter|n-shot|        Metric         |   |Value |   |Stderr|
|------|------:|------|-----:|-----------------------|---|-----:|---|------|
|ifeval|      4|none  |     0|inst_level_loose_acc   |↑  |0.7854|±  |   N/A|
|      |       |none  |     0|inst_level_strict_acc  |↑  |0.7590|±  |   N/A|
|      |       |none  |     0|prompt_level_loose_acc |↑  |0.7079|±  |0.0196|
|      |       |none  |     0|prompt_level_strict_acc|↑  |0.6691|±  |0.0202|

I'm re-running gsm8k and ifeval with reasoning enabled (the above results are without reasoning). I also believe that gpqa_diamond_cot_zeroshot can be improved with a system prompt that requests proper output format.

tarruda changed discussion title from Some lm-evaluation-harness results to Some lm-evaluation-harness results for smol-IQ2_XS Feb 24

ubergarm

Owner Feb 24

Really appreciate you taking the time to run this!

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