Instructions to use JAYLSTUDI/Prismat-2.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use JAYLSTUDI/Prismat-2.3 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 JAYLSTUDI/Prismat-2.3:Q8_0
# Run inference directly in the terminal:
llama cli -hf JAYLSTUDI/Prismat-2.3:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf JAYLSTUDI/Prismat-2.3:Q8_0
# Run inference directly in the terminal:
llama cli -hf JAYLSTUDI/Prismat-2.3: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 JAYLSTUDI/Prismat-2.3:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf JAYLSTUDI/Prismat-2.3:Q8_0

Use Docker

docker model run hf.co/JAYLSTUDI/Prismat-2.3:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use JAYLSTUDI/Prismat-2.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JAYLSTUDI/Prismat-2.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JAYLSTUDI/Prismat-2.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JAYLSTUDI/Prismat-2.3:Q8_0

Ollama
How to use JAYLSTUDI/Prismat-2.3 with Ollama:
```
ollama run hf.co/JAYLSTUDI/Prismat-2.3:Q8_0
```
Unsloth Desktop

How to use JAYLSTUDI/Prismat-2.3 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JAYLSTUDI/Prismat-2.3: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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "JAYLSTUDI/Prismat-2.3:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use JAYLSTUDI/Prismat-2.3 with Docker Model Runner:
```
docker model run hf.co/JAYLSTUDI/Prismat-2.3:Q8_0
```

Lemonade

How to use JAYLSTUDI/Prismat-2.3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull JAYLSTUDI/Prismat-2.3:Q8_0

Run and chat with the model

lemonade run user.Prismat-2.3-Q8_0

List all available models

lemonade list

Hermes Agent

How to use JAYLSTUDI/Prismat-2.3 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JAYLSTUDI/Prismat-2.3: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 JAYLSTUDI/Prismat-2.3:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use JAYLSTUDI/Prismat-2.3 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JAYLSTUDI/Prismat-2.3: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 "JAYLSTUDI/Prismat-2.3: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"

💎 Prismat-2.3 (1.5B) by JAYLAI

Prismat-2.3 is a compact, high-performance autonomous coding agent fine-tuned from Qwen2.5-Coder-1.5B-Instruct.

Developed by the JAYLAI team, it is specialized in solving competitive programming challenges (LeetCode Hard), strict algorithmic time-complexity optimization ($O(1) / O(N)$), and interactive multi-turn code review.

🚀 Key Highlights

🧠 Deep Reasoning (<think>): Analyzes edge cases, invariants, and asymptotic bounds before generating code.
⚡ Algorithmic Precision: Native intuition for advanced data structures (heapq, deque, OrderedDict, graph topological sorts, and dynamic programming).
🔄 Interactive Self-Correction: Listens to user feedback and compiler errors to refactor algorithms on the fly.
🪶 Ultra-Lightweight (GGUF Q8_0): Runs 100% offline on any standard laptop or CPU (1.65 GB).

🧪 Benchmark Verification (LeetCode Hard)

All solutions verified through automated test suites:

LRU Cache: Strict $O(1)$ operations via OrderedDict (PASSED ✅)
Trapping Rain Water: Two-pointer technique in $O(N)$ time & $O(1)$ space (PASSED ✅)
Sliding Window Maximum: Monotonic queue implementation (PASSED ✅)
Course Schedule II: Kahn's algorithm for DAG cycle detection (PASSED ✅)
Longest Valid Parentheses: Index stack in single pass (PASSED ✅)
Reconstruct Itinerary: Hierholzer's post-order DFS for Eulerian path (PASSED ✅)

💻 Quickstart (Ollama)

Create a Modelfile:

FROM ./Prismat-2.3-JAYLAI-Q8_0.gguf
SYSTEM "You are Prismat-2.3, an autonomous AI code agent created by JAYLAI. Always deliberate in <think>...</think>, then output clean, optimal Python code."
PARAMETER temperature 0.2
PARAMETER stop "<|im_end|>"

Run in terminal:

ollama create prismat -f Modelfile
ollama run prismat

📜 License

Released under the Apache 2.0 License (Open Source and Commercial friendly).

Downloads last month: 41

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

8-bit

Model tree for JAYLSTUDI/Prismat-2.3

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B-Instruct

Quantized

(193)

this model