Instructions to use batiai/Qwen3.6-35B-A3B-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 batiai/Qwen3.6-35B-A3B-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 batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf batiai/Qwen3.6-35B-A3B-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 batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf batiai/Qwen3.6-35B-A3B-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 batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf batiai/Qwen3.6-35B-A3B-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 batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use batiai/Qwen3.6-35B-A3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "batiai/Qwen3.6-35B-A3B-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": "batiai/Qwen3.6-35B-A3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M

Ollama
How to use batiai/Qwen3.6-35B-A3B-GGUF with Ollama:
```
ollama run hf.co/batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use batiai/Qwen3.6-35B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf batiai/Qwen3.6-35B-A3B-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": "batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use batiai/Qwen3.6-35B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M
```

Lemonade

How to use batiai/Qwen3.6-35B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use batiai/Qwen3.6-35B-A3B-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 batiai/Qwen3.6-35B-A3B-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 batiai/Qwen3.6-35B-A3B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use batiai/Qwen3.6-35B-A3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf batiai/Qwen3.6-35B-A3B-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 "batiai/Qwen3.6-35B-A3B-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"

hero775 commited on Apr 17

Commit

0cd0345

verified ·

1 Parent(s): 48f98a6

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +43 -4

README.md CHANGED Viewed

@@ -136,15 +136,54 @@ Only 9 of 256 experts fire per token — same reasoning capacity, far less compu
 ## On-device Benchmarks (measured)
-Measured tokens/s on your Mac — update this card with your own numbers:
 ```bash
 ollama run batiai/qwen3.6-35b:iq4 --verbose "Write a haiku about Seoul in autumn."
 ```
-| Mac | IQ3_XXS | IQ4_XS |
-|-----|--------:|-------:|
-| _pending community measurements_ | — | — |
 ## Note on the "3.6" Naming

 ## On-device Benchmarks (measured)
+Measured with BatiAI's bench harness on real Apple Silicon:
+### MacBook Pro M4 Max (128 GB RAM) — 100 % GPU
+| Metric                 | IQ3_XXS | IQ4_XS |
+|------------------------|--------:|-------:|
+| **Gen speed (warm)**   | **45.9 t/s** | **46.5 t/s** |
+| Gen range (3 runs)     | 45.6 – 46.2 | 45.0 – 48.2 |
+| Prompt eval            | 104.9 t/s | 105.0 t/s |
+| Long response (300 t)  | 45.2 t/s | 45.6 t/s |
+| Cold-start first gen   | 49.7 t/s | 51.3 t/s |
+| Load time              | 3.0 s | 5.3 s |
+| Ollama RAM (w/ KV)     | 18 GB | 23 GB |
+| Korean generation      | ✅ | ✅ |
+| **Tool call JSON**     | ❌ **fail** | ✅ pass |
+### Mac mini M4 (16 GB RAM) — community-reported
+| Model | Gen speed |
+|-------|----------:|
+| **IQ3_XXS** | ~2 – 3 t/s |
+| IQ4_XS | ❌ does not fit (needs 24 GB+) |
+IQ3 fits in 16 GB but exercises swap — usable for single-turn prompts but not for streaming chat.
+### Key take-aways
+- **On M4 Max, IQ3 and IQ4 are nearly identical in speed (~1 % apart)** — the MoE + Gated DeltaNet architecture is memory-bandwidth-bound, not compute-bound, at this quant range. Pick IQ4 unless RAM is tight.
+- **~1.75× faster than Qwen 3.5-35B-A3B IQ4** on the same M4 Max (46.5 vs 26.6 t/s measured previously).
+- **IQ3 can fail function-call JSON** — quantization cost shows up on structured output first. If your workflow uses tool calling, **choose IQ4**.
+- Both quants run 100 % on Apple Silicon GPU / Metal. No CPU fallback on machines that fit.
+- Prompt evaluation is very fast (105 t/s) — long-context RAG / agent flows feel responsive.
+### Try it yourself
 ```bash
 ollama run batiai/qwen3.6-35b:iq4 --verbose "Write a haiku about Seoul in autumn."
 ```
+Or run the full benchmark harness (cold start, 3× warm runs, long response, Korean, tool call, RAM delta):
+```bash
+# Single model
+./bench.sh           # interactive menu — pick by number
+# Share the JSON — we'll update this card
+reports/bench-*.json
+```
 ## Note on the "3.6" Naming