Qwen3.8-27Bをllama.cpp on DGX Sparkで動かし、Claude Codeから使用するメモ
on DGX Spark:
— Georgi Gerganov (@ggerganov) August 14, 2026
llama serve \
-hf ggml-org/Qwen3.8-27B-GGUF:Q4_K_M \
-hfd ggml-org/Qwen3.8-27B-GGUF:Q4_0 \
--spec-default \
--spec-type draft-mtp \
--reasoning-preserve --agent
llama.cppのビルド
mkdir -p ~/git
cd ~/git
git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
sudo apt update
sudo apt install libcurl4-openssl-dev libssl-dev -y
rm -rf build
mkdir -p build
cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES="121" -DBUILD_SHARED_LIBS=OFF
cmake --build build --config Release -j 20 --clean-first
$ ./build/bin/llama --version
version: 0.1.0-dev (build 10454, commit 4df29be4f)
built with GNU 13.3.0 for Linux aarch64
サービスの登録と起動
cat <<EOF | sudo tee /etc/systemd/system/llama-server.service > /dev/null
[Unit]
Description=llama server
After=network.target
[Service]
User=$USER
Group=$USER
WorkingDirectory=$HOME/git/llama.cpp/build
ExecStart=$HOME/git/llama.cpp/build/bin/llama serve \\
-hf ggml-org/Qwen3.8-27B-GGUF:Q4_K_M \\
-hfd ggml-org/Qwen3.8-27B-GGUF:Q4_0 \\
--spec-default \\
--spec-type draft-mtp \\
--reasoning-preserve \\
--reasoning-effort low \\
--agent \\
--chat-template-file $HOME/.config/llama.cpp/qwen3.8-midsystem.jinja \\
--host 0.0.0.0 \\
--port 8888
Restart=always
RestartSec=5
LimitNOFILE=65535
[Install]
WantedBy=multi-user.target
EOF
--chat-template-file に以下のjijaテンプレートを設定しないと、Claude Codeからは次のエラーメッセージが出ました。
While executing CallExpression at line 106, column 32 in source:
...first %}↵ {{- raise_exception('System message must be at the beginnin...
^
Error: Jinja Exception: System message must be at the beginning. This is a server-side issue, usually temporary — try again in a moment.
mkdir -p $HOME/.config/llama.cpp
cat <<'EOF' > $HOME/.config/llama.cpp/qwen3.8-midsystem.jinja
{%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
{%- if content is string %}
{{- content }}
{%- elif content is iterable and content is not mapping %}
{%- for item in content %}
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain images.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set image_count.value = image_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Picture ' ~ image_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
{%- elif 'video' in item or item.type == 'video' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain videos.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set video_count.value = video_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Video ' ~ video_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
{%- elif 'text' in item %}
{{- item.text }}
{%- else %}
{{- raise_exception('Unexpected item type in content.') }}
{%- endif %}
{%- endfor %}
{%- elif content is none or content is undefined %}
{{- '' }}
{%- else %}
{{- raise_exception('Unexpected content type.') }}
{%- endif %}
{%- endmacro %}
{%- if not messages %}
{{- raise_exception('No messages provided.') }}
{%- endif %}
{%- set reasoning_instructions = '' %}
{%- if enable_thinking is undefined or enable_thinking is true %}
{%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
{%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
{{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
{%- endif %}
{%- if resolved_reasoning_effort == 'xhigh' %}
{%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
{%- elif resolved_reasoning_effort == 'low' %}
{%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
{%- endif %}
{%- endif %}
{%- if tools and tools is iterable and tools is not mapping %}
{{- '<|im_start|>system\n' }}
{%- if reasoning_instructions %}
{{- reasoning_instructions + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>" }}
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
{%- if messages[0].role == 'system' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{%- if content %}
{{- '\n\n' + content }}
{%- endif %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if messages[0].role == 'system' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{%- if content %}
{{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }}
{%- elif reasoning_instructions %}
{{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
{%- endif %}
{%- elif reasoning_instructions %}
{{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" %}
{%- set content = render_content(message.content, false)|trim %}
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if ns.multi_step_tool %}
{{- raise_exception('No user query found in messages.') }}
{%- endif %}
{%- for message in messages %}
{%- set content = render_content(message.content, true)|trim %}
{%- if message.role == "system" %}
{%- if not loop.first and content %}
{{- '<|im_start|>system\n' + content + '<|im_end|>' + '\n' }}
{%- endif %}
{%- elif message.role == "user" %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- endif %}
{%- set reasoning_content = reasoning_content|trim %}
{%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{%- if loop.first %}
{%- if content|trim %}
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- else %}
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- else %}
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- if tool_call.arguments is defined and tool_call.arguments != '' %}
{%- for args_name, args_value in tool_call.arguments|items %}
{{- '<parameter=' + args_name + '>\n' }}
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
{{- args_value }}
{{- '\n</parameter>\n' }}
{%- endfor %}
{%- endif %}
{{- '</function>\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if not loop.last and loop.nextitem.role != "tool" %}
{{- '<|im_end|>\n' }}
{%- elif loop.last %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- else %}
{{- raise_exception('Unexpected message role.') }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- else %}
{{- '<think>\n' }}
{%- endif %}
{%- endif %}
EOF
sudo systemctl daemon-reload
sudo systemctl enable llama-server
sudo systemctl start llama-server
sudo systemctl status llama-server
OpenAI APIの動作確認
curl -s http://localhost:8888/v1/chat/completions \
--json '{
"model": "ggml-org/Qwen3.8-27B-GGUF:Q4_K_M",
"messages": [
{"role": "user", "content": "Give me a joke."}
]
}' | jq .
{
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"role": "assistant",
"content": "Why don't scientists trust atoms?\n\nBecause they make up everything.",
"reasoning_content": "The user wants a joke. Let me think of a good one that's clean, clever, and has a solid punchline. I'll go with a classic setup-punchline format that works well in text.\n"
}
}
],
"created": 1786945345,
"model": "ggml-org/Qwen3.8-27B-GGUF:Q4_K_M",
"system_fingerprint": "b10454-4df29be4f",
"object": "chat.completion",
"usage": {
"completion_tokens": 61,
"prompt_tokens": 45,
"total_tokens": 106,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"id": "chatcmpl-KUxmfxMsgQjQEgmeRdwgvHYl29kEMqYN",
"timings": {
"cache_n": 0,
"prompt_n": 45,
"prompt_ms": 2131.847,
"prompt_per_token_ms": 47.37437777777778,
"prompt_per_second": 21.108456657536866,
"predicted_n": 61,
"predicted_ms": 2220.93,
"predicted_per_token_ms": 37.015499999999996,
"predicted_per_second": 27.01570963515284,
"draft_n": 57,
"draft_n_accepted": 42
}
}
Claude Codeから動作確認
cat <<'EOF' > ~/cc-qwen.sh
#!/bin/bash
unset ANTHROPIC_API_KEY
export ANTHROPIC_BASE_URL=http://localhost:8888
export ANTHROPIC_AUTH_TOKEN=local
export ANTHROPIC_MODEL=ggml-org/Qwen3.8-27B-GGUF:Q4_K_M[256k]
export ANTHROPIC_CUSTOM_MODEL_OPTION=$ANTHROPIC_MODEL
export ANTHROPIC_DEFAULT_SONNET_MODEL=$ANTHROPIC_MODEL
export ANTHROPIC_DEFAULT_HAIKU_MODEL=$ANTHROPIC_MODEL
export ANTHROPIC_DEFAULT_OPUS_MODEL=$ANTHROPIC_MODEL
export CLAUDE_CODE_SUBAGENT_MODEL=$ANTHROPIC_MODEL
export ANTHROPIC_CUSTOM_MODEL_OPTION=$ANTHROPIC_MODEL
export ANTHROPIC_CUSTOM_MODEL_OPTION_NAME=$ANTHROPIC_MODEL
export ANTHROPIC_CUSTOM_MODEL_OPTION_DESCRIPTION=$ANTHROPIC_MODEL
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
export CLAUDE_CODE_DISABLE_NONSTREAMING_FALLBACK=1
export CLAUDE_STREAM_IDLE_TIMEOUT_MS=600000
export CLAUDE_CODE_AUTO_COMPACT_WINDOW=500000
echo "Model: $ANTHROPIC_MODEL"
set -ex
claude --dangerously-skip-permissions $@
EOF
chmod +x ~/cc-qwen.sh
~/cc-qwen.sh
