Instructions to use bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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 bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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 bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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 bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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 bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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 bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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": "bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M
- Ollama
How to use bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF with Ollama:
ollama run hf.co/bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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": "bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF with Docker Model Runner:
docker model run hf.co/bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M
- Lemonade
How to use bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.ai21labs_AI21-Jamba-Reasoning-3B-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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 bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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 bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use bartowski/ai21labs_AI21-Jamba-Reasoning-3B-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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 "bartowski/ai21labs_AI21-Jamba-Reasoning-3B-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"
GGUF seems broken on latest llama.cpp
The q4km from ai21labs themselves works
@AaronFeng753 thanks for pointing it out, there was a tokenizer issue that I think i've fixed now (tested the bf16 locally and it worked), can you give it another try?
Also seems to work fine in lmstudio now (though thinking tags aren't being properly accounted for at this time somehow)
Also seems to work fine in lmstudio now (though thinking tags aren't being properly accounted for at this time somehow)
Hi, I've noticed the missing think tags in LM Studio using the official F16 GGUF. It is weird seeing how it worked well for @AaronFeng753 in OpenWebUI? Is it using different backend than LM Studio, maybe? But I guess this is connected through the API, maybe it works in server mode, but not in the LM Studio UI directly?
The model itself works fine, but something seems still wrong with the jinja template. This happens when I try to use the model with tools:
500: 500 Trying to call method 'startswith' on null at row 37, column 84:
{%- if not loop.last %}
{%- if loop.nextitem.role == 'assistant' and loop.nextitem.content.startswith('<think>') or loop.nextitem.reasoning_content is defined and loop.nextitem.reasoning_content is not none %}
^
[...]
I am using this template without issues:
{%- set thinking_prefix = thinking_prefix or 'Begin by thinking about the reasoning process in the mind within <think> </think> tags and then proceed to give your response.\n' -%} {%- if bos_token is defined and bos_token is not none %}{{- bos_token -}}{%- endif %} {%- if tools %} {{- '<|im_start|>system\n' }} {%- if messages|length > 0 and messages[0].role == 'system' %} {{- messages[0].content + '\n\n' }} {%- endif %} {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }} {%- for tool in tools %} {{- "\n" }} {{- tool | tojson }} {%- endfor %} {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }} {%- else %} {%- if messages|length > 0 and messages[0].role == 'system' %} {{- '<|im_start|>system\n' + messages[0].content + '<|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" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %} {%- set ns.multi_step_tool = false %} {%- set ns.last_query_index = index %} {%- endif %} {%- endfor %} {%- for message in messages %} {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} {%- set prefix = '' %} {%- if message.role == 'user' and '<think>' not in message.content %} {%- if loop.last %} {%- set prefix = thinking_prefix %} {%- endif %} {%- if not loop.last %} {%- if loop.nextitem.role == 'assistant' and (loop.nextitem.content is not none and loop.nextitem.content.startswith('<think>')) or loop.nextitem.reasoning_content is defined and loop.nextitem.reasoning_content is not none %} {%- set prefix = thinking_prefix %} {%- endif %} {%- endif %} {%- endif %} {%- if message.role == 'user' and not loop.last and loop.nextitem.role == 'assistant' and (loop.nextitem.content is not none and loop.nextitem.content.startswith('<think>')) and '<think>' not in message.content %} {%- set prefix = thinking_prefix %} {%- endif %} {{- '<|im_start|>' + message.role + '\n' + prefix + message.content + '<|im_end|>' + '\n' }} {%- elif message.role == "assistant" %} {%- set content = message.content %} {%- set reasoning_content = '' %} {%- if message.reasoning_content is defined and message.reasoning_content is not none %} {%- set reasoning_content = message.reasoning_content %} {%- else %} {%- if '</think>' in message.content %} {%- set content = message.content.split('</think>')[-1].lstrip('\n') %} {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %} {%- endif %} {%- endif %} {%- if loop.index0 > ns.last_query_index %} {%- if reasoning_content %} {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }} {%- else %} {{- '<|im_start|>' + message.role + '\n' + content }} {%- endif %} {%- else %} {{- '<|im_start|>' + message.role + '\n' + content }} {%- endif %} {%- if message.tool_calls %} {%- for tool_call in message.tool_calls %} {%- if (loop.first and content) or (not loop.first) %} {{- '\n' }} {%- endif %} {%- if tool_call.function %} {%- set tool_call = tool_call.function %} {%- endif %} {{- '<tool_call>\n{"name": "' }} {{- tool_call.name }} {{- '", "arguments": ' }} {%- if tool_call.arguments is string %} {{- tool_call.arguments }} {%- else %} {{- tool_call.arguments | tojson }} {%- endif %} {{- '}\n</tool_call>' }} {%- endfor %} {%- endif %} {{- '<|im_end|>\n' }} {%- elif message.role == "tool" %} {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} {{- '<|im_start|>user' }} {%- endif %} {{- '\n<tool_response>\n' }} {{- message.content }} {{- '\n</tool_response>' }} {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} {{- '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<|im_start|>assistant\n' }} {{- '<think>\n' }} {%- endif -%}

