Instructions to use KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-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 KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
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 KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
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 KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
Use Docker
docker model run hf.co/KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
- LM Studio
- Jan
- vLLM
How to use KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-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": "KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
- Ollama
How to use KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF with Ollama:
ollama run hf.co/KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
- Unsloth Studio
How to use KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-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 KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-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 KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF to start chatting
- Pi
How to use KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
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": "KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- OpenClaw new
How to use KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
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 "KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0" \ --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 KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF with Docker Model Runner:
docker model run hf.co/KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
- Lemonade
How to use KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
Run and chat with the model
lemonade run user.Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-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 KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
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 KartoffelToby/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF:Q8_0
Run Hermes
hermes
- Atomic Chat
Update template
Browse files|
@@ -1,50 +1,20 @@
|
|
| 1 |
-
{{-
|
| 2 |
-
{{-
|
| 3 |
-
{{- if .
|
| 4 |
-
{{ .System }}
|
| 5 |
{{- end }}
|
| 6 |
-
{{-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
<
|
| 14 |
-
{{- range .Tools }}
|
| 15 |
-
{"type": "function", "function": {{ .Function }}}
|
| 16 |
{{- end }}
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
<tool_call>
|
| 21 |
-
{"name": <function-name>, "arguments": <args-json-object>}
|
| 22 |
-
</tool_call>
|
| 23 |
-
{{- end }}<|im_end|>
|
| 24 |
-
{{ end }}
|
| 25 |
-
{{- range $i, $_ := .Messages }}
|
| 26 |
-
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
|
| 27 |
-
{{- if eq .Role "user" }}<|im_start|>user
|
| 28 |
-
{{ .Content }}<|im_end|>
|
| 29 |
-
{{ else if eq .Role "assistant" }}<|im_start|>assistant
|
| 30 |
-
{{ if .Content }}{{ .Content }}
|
| 31 |
-
{{- else if .ToolCalls }}<tool_call>
|
| 32 |
-
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
|
| 33 |
-
{{ end }}</tool_call>
|
| 34 |
-
{{- end }}{{ if not $last }}<|im_end|>
|
| 35 |
-
{{ end }}
|
| 36 |
-
{{- else if eq .Role "tool" }}<|im_start|>user
|
| 37 |
-
<tool_response>
|
| 38 |
-
{{ .Content }}
|
| 39 |
-
</tool_response><|im_end|>
|
| 40 |
-
{{ end }}
|
| 41 |
-
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
|
| 42 |
-
{{ end }}
|
| 43 |
{{- end }}
|
| 44 |
-
{{- else }}
|
| 45 |
-
{{-
|
| 46 |
-
{{
|
| 47 |
-
{{ end }}{{ if .Prompt }}<|im_start|>user
|
| 48 |
-
{{ .Prompt }}<|im_end|>
|
| 49 |
-
{{ end }}<|im_start|>assistant
|
| 50 |
-
{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}
|
|
|
|
| 1 |
+
{{- $lastUserIndex := -1 }}
|
| 2 |
+
{{- range $index, $_ := .Messages }}
|
| 3 |
+
{{- if eq .Role "user" }}{{ $lastUserIndex = $index }}{{ end }}
|
|
|
|
| 4 |
{{- end }}
|
| 5 |
+
{{- range $index, $_ := .Messages }}
|
| 6 |
+
{{- if eq .Role "system" }}[SYSTEM_PROMPT]{{ .Content }}[/SYSTEM_PROMPT]
|
| 7 |
+
{{- else if eq .Role "user" }}
|
| 8 |
+
{{- if and (eq $lastUserIndex $index) $.Tools }}[AVAILABLE_TOOLS]{{ $.Tools }}[/AVAILABLE_TOOLS]
|
| 9 |
+
{{- end }}[INST]{{ .Content }}[/INST]
|
| 10 |
+
{{- else if eq .Role "assistant" }}
|
| 11 |
+
{{- if .Content }}{{ .Content }}
|
| 12 |
+
{{- if not (eq (len (slice $.Messages $index)) 1) }}</s>
|
|
|
|
|
|
|
| 13 |
{{- end }}
|
| 14 |
+
{{- else if .ToolCalls }}[TOOL_CALLS][
|
| 15 |
+
{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
|
| 16 |
+
{{- end }}]</s>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
{{- end }}
|
| 18 |
+
{{- else if eq .Role "tool" }}[TOOL_RESULTS]{"content": {{ .Content }}}[/TOOL_RESULTS]
|
| 19 |
+
{{- end }}
|
| 20 |
+
{{- end }}
|
|
|
|
|
|
|
|
|
|
|
|