Instructions to use Cheva123/Jamjuri-Preview-9B 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 Cheva123/Jamjuri-Preview-9B 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 Cheva123/Jamjuri-Preview-9B:Q8_0 # Run inference directly in the terminal: llama cli -hf Cheva123/Jamjuri-Preview-9B:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Cheva123/Jamjuri-Preview-9B:Q8_0 # Run inference directly in the terminal: llama cli -hf Cheva123/Jamjuri-Preview-9B:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Cheva123/Jamjuri-Preview-9B:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf Cheva123/Jamjuri-Preview-9B:Q8_0
Use Docker
docker model run hf.co/Cheva123/Jamjuri-Preview-9B:Q8_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use Cheva123/Jamjuri-Preview-9B with Ollama:
ollama run hf.co/Cheva123/Jamjuri-Preview-9B:Q8_0
- Unsloth Desktop
- Pi
How to use Cheva123/Jamjuri-Preview-9B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Cheva123/Jamjuri-Preview-9B:Q8_0
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Cheva123/Jamjuri-Preview-9B:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Cheva123/Jamjuri-Preview-9B with Docker Model Runner:
docker model run hf.co/Cheva123/Jamjuri-Preview-9B:Q8_0
- Lemonade
How to use Cheva123/Jamjuri-Preview-9B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Cheva123/Jamjuri-Preview-9B:Q8_0
Run and chat with the model
lemonade run user.Jamjuri-Preview-9B-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use Cheva123/Jamjuri-Preview-9B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Cheva123/Jamjuri-Preview-9B: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://127.0.0.1:9931/v1 hermes config set model.default Cheva123/Jamjuri-Preview-9B:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Cheva123/Jamjuri-Preview-9B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Cheva123/Jamjuri-Preview-9B: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://127.0.0.1:9931/v1 \ --custom-model-id "Cheva123/Jamjuri-Preview-9B: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"
- Jamjuri β Preview
- What this preview is
- Model
- Early benchmark snapshot
- Intended use
- Not intended for
- Release philosophy
- Jamjuri Preview ΰΈΰΈ·ΰΈΰΈΰΈ°ΰΉΰΈ£
- ΰΈΰΉΰΈΰΈ‘ΰΈΉΰΈ₯ΰΉΰΈ‘ΰΉΰΈΰΈ₯
- ΰΈΰΈ₯ Benchmark ΰΉΰΈΰΈ·ΰΉΰΈΰΈΰΈΰΉΰΈ
- ΰΉΰΈ«ΰΈ‘ΰΈ²ΰΈ°ΰΈͺΰΈ³ΰΈ«ΰΈ£ΰΈ±ΰΈ
- ΰΉΰΈ‘ΰΉΰΉΰΈ«ΰΈ‘ΰΈ²ΰΈ°ΰΈͺΰΈ³ΰΈ«ΰΈ£ΰΈ±ΰΈ
- ΰΉΰΈΰΈ§ΰΈΰΈ²ΰΈΰΈΰΈΰΈ Preview
- Local inference
- Release files
- Cheva Labs
- What this preview is
Jamjuri β Preview
Jamjuri is the first fine-tuned model released by Cheva Labs.
Target Hub repository: Cheva123/Jamjuri-Preview-9B
Published artifact: JamjuriLLM-9B-Q8_0.gguf only
Series: part of Jamjuri 9B β collection Β· series card Series: part of the Jamjuri 9B series Β· collection
This preview is an early experiment focused on practical Thai SME workflows: Thai communication, document drafting, RAG, tool use, and simple business automation.
Experimental preview β do not use this model for production or real business operations.
Jamjuri is still in a very early stage of development. Its outputs may be incomplete, incorrect, inconsistent, or unsafe for real-world decisions. Do not rely on it for financial, legal, medical, operational, or other high-impact work.
English
What this preview is
Jamjuri Preview is Cheva Labs' first public fine-tuned model. The goal of this release is not to present a finished production model, but to document an early step toward a Thai-first local AI assistant for small and medium-sized businesses.
Current areas of focus:
- Thai workplace communication
- Document and business writing
- Retrieval-Augmented Generation (RAG)
- Tool / function calling
- Simple workflow automation
- Preserving general reasoning, math, coding, and instruction-following ability
Model
- Base model: Qwen3.5-9B
- Post-training: 3 Expert LoRA + merge
- Primary preview format: GGUF Q8_0
- Languages: Thai and English
- Status: Experimental research preview
Early benchmark snapshot
The table below is an early, vendor-selected evaluation subset used during development. It is not a complete benchmark suite, does not measure 100% of model capability, and should not be treated as a universal ranking.
| Benchmark | Qwen Q8 | Jamjuri Q8 | Difference |
|---|---|---|---|
| BFCL V4 β simple_python | 94.00% | 93.00% | -1.00 pp |
| IFEval β strict | 83.36% | 84.10% | +0.74 pp |
| Thai Eval β Belebele fallback | 75.00% | 80.78% | +5.78 pp |
| GSM8K β strict | 83.40% | 84.84% | +1.44 pp |
| MMLU-Pro β 700-sample gate | 72.57% | 73.29% | +0.71 pp |
| HumanEval+ β pass@1 | 82.90% | 84.80% | +1.90 pp |
| MBPP+ β pass@1 | 65.90% | 64.30% | -1.60 pp |
In this development snapshot, Jamjuri scored higher on 5 of the 7 selected no-thinking evaluations. These results are useful for internal comparison, but they are not sufficient to claim broad superiority over the base model.
ΟΒ³ Retail result
A thinking-mode ΟΒ³ Retail run completed 114/114 terminal simulations for both models. Mean reward on reward-bearing records was 15.91% for Qwen (7/44) and 24.07% for Jamjuri (13/54). However, the two runs did not use an identical external judge route, so this result is treated as directional evidence only, not a controlled apples-to-apples benchmark. Infrastructure errors were recorded in both runs.
A broader set of standard and community benchmarks will be published later after the evaluation setup is made more reproducible and complete.
Intended use
This model is intended for:
- Research and experimentation
- Local inference testing
- Thai SME workflow prototyping
- RAG / tool-use experiments
- Benchmarking and evaluation
Not intended for
Do not use this preview as a production business assistant or autonomous decision-maker.
Avoid using it for:
- Financial decisions or accounting approval
- Legal advice or legal document approval
- Medical or safety-critical decisions
- Autonomous purchases, payments, or irreversible actions
- Production customer support without human review
- Any workflow where an incorrect answer can cause material harm
Release philosophy
Jamjuri Preview is being released early so the work can be documented, tested, and improved in public. The model is expected to change substantially in later versions.
ΰΈ ΰΈ²ΰΈ©ΰΈ²ΰΉΰΈΰΈ’
Jamjuri Preview ΰΈΰΈ·ΰΈΰΈΰΈ°ΰΉΰΈ£
Jamjuri Preview ΰΉΰΈΰΉΰΈΰΉΰΈ‘ΰΉΰΈΰΈ₯ Fine-tune ΰΈΰΈ±ΰΈ§ΰΉΰΈ£ΰΈΰΈΰΈ΅ΰΉ Cheva Labs ΰΈΰΈ₯ΰΉΰΈΰΈ’ΰΈͺΰΈΉΰΉΰΈͺΰΈ²ΰΈΰΈ²ΰΈ£ΰΈΰΈ° ΰΉΰΈΰΈ’ΰΉΰΈΰΉΰΈ²ΰΈ«ΰΈ‘ΰΈ²ΰΈ’ΰΈΰΈΰΈΰΈ£ΰΈΈΰΉΰΈΰΈΰΈ΅ΰΉΰΉΰΈ‘ΰΉΰΉΰΈΰΉΰΈΰΈ²ΰΈ£ΰΉΰΈΰΉΰΈΰΉΰΈ‘ΰΉΰΈΰΈ₯ΰΈΰΈ£ΰΉΰΈΰΈ‘ΰΉΰΈΰΉΰΈΰΈ²ΰΈΰΈΰΈ£ΰΈ΄ΰΈ ΰΉΰΈΰΉΰΉΰΈΰΉΰΈΰΈΰΉΰΈ²ΰΈ§ΰΉΰΈ£ΰΈΰΈΰΈΰΈΰΈΰΈ²ΰΈ£ΰΈΰΈΰΈ₯ΰΈΰΈΰΈΰΈ±ΰΈΰΈΰΈ² Local AI ΰΈΰΈ΅ΰΉΰΉΰΈΰΉΰΈΰΈΰΈ²ΰΈ£ΰΉΰΈΰΉΰΈΰΈ²ΰΈΰΉΰΈΰΈΰΈ£ΰΈ΄ΰΈΰΈΰΈΰΈΰΈ SME ΰΉΰΈΰΈ’
ΰΈΰΈ§ΰΈ²ΰΈ‘ΰΈͺΰΈ²ΰΈ‘ΰΈ²ΰΈ£ΰΈΰΈΰΈ΅ΰΉΰΈΰΈ³ΰΈ₯ΰΈ±ΰΈΰΈΰΈ±ΰΈΰΈΰΈ²ΰΉΰΈΰΈ£ΰΈΈΰΉΰΈΰΈΰΈ΅ΰΉ ΰΉΰΈΰΉΰΉΰΈΰΉ
- ΰΈΰΈ²ΰΈ£ΰΈͺΰΈ·ΰΉΰΈΰΈͺΰΈ²ΰΈ£ΰΈ ΰΈ²ΰΈ©ΰΈ²ΰΉΰΈΰΈ’ΰΉΰΈΰΈΰΈ£ΰΈ΄ΰΈΰΈΰΈΰΈ²ΰΈ£ΰΈΰΈ³ΰΈΰΈ²ΰΈ
- ΰΈΰΈ²ΰΈ£ΰΉΰΈΰΈ΅ΰΈ’ΰΈΰΉΰΈΰΈΰΈͺΰΈ²ΰΈ£ΰΉΰΈ₯ΰΈ°ΰΈΰΉΰΈΰΈΰΈ§ΰΈ²ΰΈ‘ΰΈΰΈ²ΰΈΰΈΰΈΈΰΈ£ΰΈΰΈ΄ΰΈ
- Retrieval-Augmented Generation (RAG)
- Tool / Function Calling
- Workflow automation ΰΉΰΈΰΈΰΈΰΈ·ΰΉΰΈΰΈΰΈ²ΰΈ
- ΰΈΰΈ²ΰΈ£ΰΈ£ΰΈ±ΰΈΰΈ©ΰΈ²ΰΈΰΈ§ΰΈ²ΰΈ‘ΰΈͺΰΈ²ΰΈ‘ΰΈ²ΰΈ£ΰΈΰΉΰΈΰΈ΄ΰΈ‘ΰΈΰΉΰΈ²ΰΈ Reasoning, Math, Coding ΰΉΰΈ₯ΰΈ° Instruction Following
ΰΈΰΉΰΈΰΈ‘ΰΈΉΰΈ₯ΰΉΰΈ‘ΰΉΰΈΰΈ₯
- Base model: Qwen3.5-9B
- Post-training: 3 Expert LoRA + Merge
- ΰΈ£ΰΈΉΰΈΰΉΰΈΰΈ Preview ΰΈ«ΰΈ₯ΰΈ±ΰΈ: GGUF Q8_0
- ΰΈ ΰΈ²ΰΈ©ΰΈ²: ΰΉΰΈΰΈ’ΰΉΰΈ₯ΰΈ°ΰΈΰΈ±ΰΈΰΈΰΈ€ΰΈ©
- ΰΈͺΰΈΰΈ²ΰΈΰΈ°: Experimental Research Preview
ΰΉΰΈ‘ΰΉΰΈΰΈ§ΰΈ£ΰΈΰΈ³ Jamjuri Preview ΰΉΰΈΰΉΰΈΰΉΰΉΰΈΰΈΰΈ²ΰΈΰΈΰΈ£ΰΈ΄ΰΈΰΈ«ΰΈ£ΰΈ·ΰΈΰΈ£ΰΈ°ΰΈΰΈ Production
ΰΉΰΈ‘ΰΉΰΈΰΈ₯ΰΈ’ΰΈ±ΰΈΰΈΰΈ’ΰΈΉΰΉΰΉΰΈΰΈΰΉΰΈ§ΰΈΰΈΰΈΰΈ₯ΰΈΰΈΰΈ£ΰΈ°ΰΈ’ΰΈ°ΰΉΰΈ£ΰΈΰΈ‘ΰΈ²ΰΈ ΰΈΰΈ³ΰΈΰΈΰΈΰΈΰΈ²ΰΈΰΈΰΈ΄ΰΈ ΰΉΰΈ‘ΰΉΰΈΰΈ£ΰΈ ΰΉΰΈ‘ΰΉΰΈͺΰΈ‘ΰΉΰΈ³ΰΉΰΈͺΰΈ‘ΰΈ ΰΈ«ΰΈ£ΰΈ·ΰΈΰΈ‘ΰΈ΅ΰΈΰΈ€ΰΈΰΈ΄ΰΈΰΈ£ΰΈ£ΰΈ‘ΰΈΰΈ΅ΰΉΰΈ’ΰΈ±ΰΈΰΉΰΈ‘ΰΉΰΉΰΈΰΉΰΈ£ΰΈ±ΰΈΰΈΰΈ²ΰΈ£ΰΈΰΈΰΈͺΰΈΰΈΰΉΰΈΰΈ΅ΰΈ’ΰΈΰΈΰΈ ΰΈΰΈΈΰΈΰΈΰΈ²ΰΈΰΈΰΈ΅ΰΉΰΈ‘ΰΈ΅ΰΈΰΈ₯ΰΈΰΈ£ΰΈ°ΰΈΰΈΰΈΰΈ£ΰΈ΄ΰΈΰΈΰΈ§ΰΈ£ΰΈ‘ΰΈ΅ΰΈ‘ΰΈΰΈΈΰΈ©ΰΈ’ΰΉΰΈΰΈ£ΰΈ§ΰΈΰΈͺΰΈΰΈΰΉΰΈͺΰΈ‘ΰΈ
ΰΈΰΈ₯ Benchmark ΰΉΰΈΰΈ·ΰΉΰΈΰΈΰΈΰΉΰΈ
ΰΈΰΈ₯ΰΈΰΉΰΈ²ΰΈΰΈ₯ΰΉΰΈ²ΰΈΰΉΰΈΰΉΰΈ ΰΈΰΈΈΰΈ Benchmark ΰΈΰΈ΅ΰΉ Cheva Labs ΰΉΰΈ₯ΰΈ·ΰΈΰΈΰΉΰΈΰΉΰΈ£ΰΈ°ΰΈ«ΰΈ§ΰΉΰΈ²ΰΈΰΈΰΈ²ΰΈ£ΰΈΰΈ±ΰΈΰΈΰΈ² ΰΉΰΈΰΉΰΈ²ΰΈΰΈ±ΰΉΰΈ ΰΉΰΈ‘ΰΉΰΉΰΈΰΉΰΈΰΈΈΰΈΰΈΰΈΰΈͺΰΈΰΈΰΈΰΈ΅ΰΉΰΈΰΈ£ΰΈΰΈΰΈΰΈ₯ΰΈΈΰΈ‘ΰΈΰΈ§ΰΈ²ΰΈ‘ΰΈͺΰΈ²ΰΈ‘ΰΈ²ΰΈ£ΰΈΰΈΰΈ±ΰΉΰΈΰΈ«ΰΈ‘ΰΈΰΈΰΈΰΈΰΉΰΈ‘ΰΉΰΈΰΈ₯ ΰΉΰΈ₯ΰΈ° ΰΉΰΈ‘ΰΉΰΉΰΈΰΉΰΈ«ΰΈ‘ΰΈ²ΰΈ’ΰΈΰΈ§ΰΈ²ΰΈ‘ΰΈ§ΰΉΰΈ²ΰΉΰΈΰΉΰΈΰΈΰΈ₯ Benchmark ΰΈͺΰΈ²ΰΈΰΈ₯ΰΉΰΈΰΈ 100%
| Benchmark | Qwen Q8 | Jamjuri Q8 | ΰΈΰΉΰΈ²ΰΈΰΈΰΈ±ΰΈ |
|---|---|---|---|
| BFCL V4 β simple_python | 94.00% | 93.00% | -1.00 pp |
| IFEval β strict | 83.36% | 84.10% | +0.74 pp |
| Thai Eval β Belebele fallback | 75.00% | 80.78% | +5.78 pp |
| GSM8K β strict | 83.40% | 84.84% | +1.44 pp |
| MMLU-Pro β 700-sample gate | 72.57% | 73.29% | +0.71 pp |
| HumanEval+ β pass@1 | 82.90% | 84.80% | +1.90 pp |
| MBPP+ β pass@1 | 65.90% | 64.30% | -1.60 pp |
ΰΉΰΈΰΈΰΈΈΰΈΰΈΰΈΰΈͺΰΈΰΈΰΉΰΈΰΈ·ΰΉΰΈΰΈΰΈΰΉΰΈΰΉΰΈΰΈ no-thinking ΰΈΰΈ΅ΰΉ Jamjuri ΰΈ‘ΰΈ΅ΰΈΰΈ°ΰΉΰΈΰΈΰΈͺΰΈΉΰΈΰΈΰΈ§ΰΉΰΈ² Base ΰΉΰΈ 5 ΰΈΰΈ²ΰΈ 7 ΰΈ£ΰΈ²ΰΈ’ΰΈΰΈ²ΰΈ£ ΰΉΰΈΰΉΰΈΰΈ₯ΰΈΰΈ΅ΰΉΰΈΰΈ§ΰΈ£ΰΈΰΈΉΰΈΰΈ‘ΰΈΰΈΰΉΰΈΰΉΰΈΰΈΰΉΰΈΰΈ‘ΰΈΉΰΈ₯ΰΈͺΰΈ³ΰΈ«ΰΈ£ΰΈ±ΰΈΰΈΰΈ²ΰΈ£ΰΉΰΈΰΈ£ΰΈ΅ΰΈ’ΰΈΰΉΰΈΰΈ΅ΰΈ’ΰΈΰΈ£ΰΈ°ΰΈ«ΰΈ§ΰΉΰΈ²ΰΈΰΈΰΈ²ΰΈ£ΰΈΰΈ±ΰΈΰΈΰΈ²ΰΉΰΈΰΉΰΈ²ΰΈΰΈ±ΰΉΰΈ ΰΉΰΈ₯ΰΈ°ΰΈ’ΰΈ±ΰΈΰΉΰΈ‘ΰΉΰΉΰΈΰΈ΅ΰΈ’ΰΈΰΈΰΈΰΈͺΰΈ³ΰΈ«ΰΈ£ΰΈ±ΰΈΰΈͺΰΈ£ΰΈΈΰΈΰΈ§ΰΉΰΈ²ΰΉΰΈ‘ΰΉΰΈΰΈ₯ΰΈΰΈ΅ΰΈΰΈ§ΰΉΰΈ² Base ΰΉΰΈΰΈ ΰΈ²ΰΈΰΈ£ΰΈ§ΰΈ‘ΰΈΰΈΈΰΈΰΈΰΉΰΈ²ΰΈ
ΟΒ³ Retail
ΰΈΰΈ²ΰΈ£ΰΈΰΈΰΈͺΰΈΰΈ ΟΒ³ Retail ΰΉΰΈΰΈ thinking-mode ΰΉΰΈͺΰΈ£ΰΉΰΈΰΈͺΰΈ΄ΰΉΰΈ 114/114 terminal simulations ΰΈͺΰΈ³ΰΈ«ΰΈ£ΰΈ±ΰΈΰΈΰΈ±ΰΉΰΈΰΈͺΰΈΰΈΰΉΰΈ‘ΰΉΰΈΰΈ₯ ΰΉΰΈΰΈ’ΰΈ‘ΰΈ΅ΰΈΰΉΰΈ² mean reward ΰΈΰΈ²ΰΈΰΈ£ΰΈ²ΰΈ’ΰΈΰΈ²ΰΈ£ΰΈΰΈ΅ΰΉΰΈ‘ΰΈ΅ reward ΰΉΰΈΰΉΰΈ²ΰΈΰΈ±ΰΈ 15.91% ΰΈͺΰΈ³ΰΈ«ΰΈ£ΰΈ±ΰΈ Qwen (7/44) ΰΉΰΈ₯ΰΈ° 24.07% ΰΈͺΰΈ³ΰΈ«ΰΈ£ΰΈ±ΰΈ Jamjuri (13/54) ΰΈΰΈ’ΰΉΰΈ²ΰΈΰΉΰΈ£ΰΈΰΉΰΈΰΈ²ΰΈ‘ ΰΈ£ΰΈΰΈΰΈΰΈΰΈͺΰΈΰΈΰΈΰΈΰΈΰΈͺΰΈΰΈΰΉΰΈ‘ΰΉΰΈΰΈ₯ΰΉΰΈ‘ΰΉΰΉΰΈΰΉΰΉΰΈΰΉ external judge route ΰΈΰΈ΅ΰΉΰΉΰΈ«ΰΈ‘ΰΈ·ΰΈΰΈΰΈΰΈ±ΰΈΰΈΰΈΈΰΈΰΈΰΈ£ΰΈ°ΰΈΰΈ²ΰΈ£ ΰΈΰΈ±ΰΈΰΈΰΈ±ΰΉΰΈΰΈΰΈ₯ΰΈΰΈ΅ΰΉΰΈΰΈ·ΰΈΰΉΰΈΰΉΰΈ directional evidence ΰΉΰΈΰΉΰΈ²ΰΈΰΈ±ΰΉΰΈ ΰΉΰΈ‘ΰΉΰΉΰΈΰΉ controlled benchmark ΰΈΰΈ΅ΰΉΰΈͺΰΈ‘ΰΈΰΈΉΰΈ£ΰΈΰΉ ΰΉΰΈ₯ΰΈ°ΰΈΰΈ±ΰΉΰΈΰΈͺΰΈΰΈΰΈ£ΰΈΰΈΰΈ‘ΰΈ΅ infrastructure error ΰΈΰΈ²ΰΈΰΈͺΰΉΰΈ§ΰΈ
Benchmark ΰΈͺΰΈ²ΰΈΰΈ₯ΰΉΰΈ₯ΰΈ° Community Benchmark ΰΈΰΈ΅ΰΉΰΈΰΈ§ΰΉΰΈ²ΰΈΰΈΰΈ§ΰΉΰΈ²ΰΈΰΈ΅ΰΉΰΈΰΈ°ΰΈΰΈ’ΰΈΰΈ’ΰΉΰΈΰΈ΄ΰΉΰΈ‘ΰΉΰΈΰΈ ΰΈ²ΰΈ’ΰΈ«ΰΈ₯ΰΈ±ΰΈ ΰΈ«ΰΈ₯ΰΈ±ΰΈΰΈΰΈ²ΰΈΰΈ£ΰΈ°ΰΈΰΈΰΈΰΈ£ΰΈ°ΰΉΰΈ‘ΰΈ΄ΰΈΰΈ‘ΰΈ΅ΰΈΰΈ§ΰΈ²ΰΈ‘ reproducible ΰΉΰΈ₯ΰΈ°ΰΈΰΈ£ΰΈΰΈΰΈΰΈ₯ΰΈΈΰΈ‘ΰΈ‘ΰΈ²ΰΈΰΈΰΈΆΰΉΰΈ
ΰΉΰΈ«ΰΈ‘ΰΈ²ΰΈ°ΰΈͺΰΈ³ΰΈ«ΰΈ£ΰΈ±ΰΈ
- ΰΈΰΈ²ΰΈΰΈ§ΰΈ΄ΰΈΰΈ±ΰΈ’ΰΉΰΈ₯ΰΈ°ΰΈΰΈ²ΰΈ£ΰΈΰΈΰΈ₯ΰΈΰΈ
- ΰΈΰΈ²ΰΈ£ΰΈΰΈΰΈͺΰΈΰΈ Local inference
- Prototype workflow ΰΈͺΰΈ³ΰΈ«ΰΈ£ΰΈ±ΰΈ SME ΰΉΰΈΰΈ’
- ΰΈΰΈ²ΰΈ£ΰΈΰΈΰΈ₯ΰΈΰΈ RAG ΰΉΰΈ₯ΰΈ° Tool Use
- Benchmark ΰΉΰΈ₯ΰΈ° Evaluation
ΰΉΰΈ‘ΰΉΰΉΰΈ«ΰΈ‘ΰΈ²ΰΈ°ΰΈͺΰΈ³ΰΈ«ΰΈ£ΰΈ±ΰΈ
ΰΉΰΈ‘ΰΉΰΈΰΈ§ΰΈ£ΰΉΰΈΰΉΰΉΰΈ‘ΰΉΰΈΰΈ₯ΰΈΰΈ΅ΰΉΰΉΰΈΰΉΰΈΰΈΰΈΉΰΉΰΈΰΉΰΈ§ΰΈ’ΰΈΰΈΈΰΈ£ΰΈΰΈ΄ΰΈΰΉΰΈ Production ΰΈ«ΰΈ£ΰΈ·ΰΈΰΈ£ΰΈ°ΰΈΰΈΰΈΰΈ±ΰΈΰΈͺΰΈ΄ΰΈΰΉΰΈΰΈΰΈ±ΰΈΰΉΰΈΰΈ‘ΰΈ±ΰΈΰΈ΄
ΰΈΰΈ§ΰΈ£ΰΈ«ΰΈ₯ΰΈ΅ΰΈΰΉΰΈ₯ΰΈ΅ΰΉΰΈ’ΰΈΰΈΰΈ²ΰΈ£ΰΉΰΈΰΉΰΈΰΈ±ΰΈ:
- ΰΈΰΈ²ΰΈ£ΰΈΰΈ±ΰΈΰΈͺΰΈ΄ΰΈΰΉΰΈΰΈΰΉΰΈ²ΰΈΰΈΰΈ²ΰΈ£ΰΉΰΈΰΈ΄ΰΈΰΈ«ΰΈ£ΰΈ·ΰΈΰΈΰΈΰΈΈΰΈ‘ΰΈ±ΰΈΰΈ΄ΰΈΰΈ±ΰΈΰΈΰΈ΅
- ΰΈΰΈ³ΰΉΰΈΰΈ°ΰΈΰΈ³ΰΈ«ΰΈ£ΰΈ·ΰΈΰΈΰΈ²ΰΈ£ΰΈΰΈΰΈΈΰΈ‘ΰΈ±ΰΈΰΈ΄ΰΉΰΈΰΈΰΈͺΰΈ²ΰΈ£ΰΈΰΉΰΈ²ΰΈΰΈΰΈΰΈ«ΰΈ‘ΰΈ²ΰΈ’
- ΰΈΰΈ²ΰΈ£ΰΉΰΈΰΈΰΈ’ΰΉΰΈ«ΰΈ£ΰΈ·ΰΈΰΈ£ΰΈ°ΰΈΰΈΰΈΰΈ΅ΰΉΰΉΰΈΰΈ΅ΰΉΰΈ’ΰΈ§ΰΈΰΉΰΈΰΈΰΈΰΈ±ΰΈΰΈΰΈ§ΰΈ²ΰΈ‘ΰΈΰΈ₯ΰΈΰΈΰΈ ΰΈ±ΰΈ’
- ΰΈΰΈ²ΰΈ£ΰΈΰΈ·ΰΉΰΈ ΰΈΰΉΰΈ²ΰΈ’ΰΉΰΈΰΈ΄ΰΈ ΰΈ«ΰΈ£ΰΈ·ΰΈΰΈΰΈ³ΰΈΰΈ³ΰΈͺΰΈ±ΰΉΰΈΰΈΰΈ΅ΰΉΰΈ’ΰΉΰΈΰΈΰΈΰΈ₯ΰΈ±ΰΈΰΉΰΈ‘ΰΉΰΉΰΈΰΉΰΉΰΈΰΈΰΈΰΈ±ΰΈΰΉΰΈΰΈ‘ΰΈ±ΰΈΰΈ΄
- Customer support ΰΈΰΈ£ΰΈ΄ΰΈΰΉΰΈΰΈ’ΰΉΰΈ‘ΰΉΰΈ‘ΰΈ΅ΰΈ‘ΰΈΰΈΈΰΈ©ΰΈ’ΰΉΰΈΰΈ£ΰΈ§ΰΈΰΈͺΰΈΰΈ
- ΰΈΰΈ²ΰΈΰΉΰΈ ΰΉ ΰΈΰΈ΅ΰΉΰΈΰΈ³ΰΈΰΈΰΈΰΈΰΈ΄ΰΈΰΈͺΰΈ²ΰΈ‘ΰΈ²ΰΈ£ΰΈΰΈͺΰΈ£ΰΉΰΈ²ΰΈΰΈΰΈ§ΰΈ²ΰΈ‘ΰΉΰΈͺΰΈ΅ΰΈ’ΰΈ«ΰΈ²ΰΈ’ΰΈΰΈ£ΰΈ΄ΰΈ
ΰΉΰΈΰΈ§ΰΈΰΈ²ΰΈΰΈΰΈΰΈ Preview
Jamjuri Preview ΰΈΰΈΉΰΈΰΈΰΈ₯ΰΉΰΈΰΈ’ΰΉΰΈΰΈΰΉΰΈ§ΰΈΰΉΰΈ£ΰΈΰΉΰΈΰΈ·ΰΉΰΈΰΉΰΈ«ΰΉΰΈͺΰΈ²ΰΈ‘ΰΈ²ΰΈ£ΰΈΰΈΰΈ±ΰΈΰΈΰΈΆΰΈΰΈΰΈ₯ ΰΈΰΈΰΈ₯ΰΈΰΈ ΰΉΰΈ₯ΰΈ°ΰΈΰΈ±ΰΈΰΈΰΈ²ΰΈΰΉΰΈΰΉΰΈΰΈΰΉΰΈΰΈ΄ΰΈΰΉΰΈΰΈ’ΰΉΰΈΰΉ ΰΉΰΈ‘ΰΉΰΈΰΈ₯ΰΈ£ΰΈΈΰΉΰΈΰΈΰΈ±ΰΈΰΉΰΈΰΈΰΈ²ΰΈΰΉΰΈΰΈ₯ΰΈ΅ΰΉΰΈ’ΰΈΰΉΰΈΰΈ₯ΰΈΰΈΰΈ²ΰΈΰΈ£ΰΈΈΰΉΰΈΰΈΰΈ΅ΰΉΰΈΰΈ’ΰΉΰΈ²ΰΈΰΈ‘ΰΈ²ΰΈ
Local inference
llama.cpp
llama-server \
--model JamjuriLLM-9B-Q8_0.gguf \
--jinja \
--ctx-size 16384 \
--n-predict 4096 \
--temperature 0.7 \
--host 127.0.0.1 \
--port 8080
The OpenAI-compatible endpoint is available at http://127.0.0.1:8080/v1.
Ollama
ollama create jamjuri:9b-q8 -f Modelfile.Q8_0
ollama run jamjuri:9b-q8
Release files
JamjuriLLM-9B-Q8_0.ggufβ the only model weight staged for this releaseModelfile.Q8_0β Ollama configurationassets/jamjuri-preview.pngβ model-card artworkMANIFEST.jsonβ local checksum and provenance record
This preview uses the Apache-2.0 license, matching the Qwen3.5-9B base model. Dataset and adapter redistribution terms should still be reviewed separately before public release.
Cheva Labs
Cheva Labs builds open, practical AI and engineering tools with an emphasis on local AI, reproducible experiments, and making advanced systems more accessible to Thai users, students, individuals, and smaller organizations.
- Downloads last month
- 12
8-bit