Instructions to use dcostenco/prism-coder-14b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dcostenco/prism-coder-14b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dcostenco/prism-coder-14b",
	filename="prism-aac-14b-q4km.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use dcostenco/prism-coder-14b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dcostenco/prism-coder-14b
# Run inference directly in the terminal:
llama-cli -hf dcostenco/prism-coder-14b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dcostenco/prism-coder-14b
# Run inference directly in the terminal:
llama-cli -hf dcostenco/prism-coder-14b

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 dcostenco/prism-coder-14b
# Run inference directly in the terminal:
./llama-cli -hf dcostenco/prism-coder-14b

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 dcostenco/prism-coder-14b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dcostenco/prism-coder-14b

Use Docker

docker model run hf.co/dcostenco/prism-coder-14b

LM Studio
Jan
Ollama
How to use dcostenco/prism-coder-14b with Ollama:
```
ollama run hf.co/dcostenco/prism-coder-14b
```

Unsloth Studio new

How to use dcostenco/prism-coder-14b 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 dcostenco/prism-coder-14b 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 dcostenco/prism-coder-14b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dcostenco/prism-coder-14b to start chatting

Pi new

How to use dcostenco/prism-coder-14b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf dcostenco/prism-coder-14b

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": "dcostenco/prism-coder-14b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dcostenco/prism-coder-14b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf dcostenco/prism-coder-14b

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 dcostenco/prism-coder-14b

Run Hermes

hermes

Docker Model Runner
How to use dcostenco/prism-coder-14b with Docker Model Runner:
```
docker model run hf.co/dcostenco/prism-coder-14b
```

Lemonade

How to use dcostenco/prism-coder-14b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dcostenco/prism-coder-14b

Run and chat with the model

lemonade run user.prism-coder-14b-{{QUANT_TAG}}

List all available models

lemonade list

prism-coder:14b — Tool Routing Model (Desktop Primary Tier)

Fine-tuned Qwen3-14B for 6-tool routing in the Prism AAC system. First tier in the desktop cascade: 14B → 32B → cloud Claude.

BFCL Routing Benchmark — v33 (Current)

Mean: 97.1% (3-seed average, seeds 2027/2028/2029, 102 cases each)

Category	Description	Accuracy
aac	AAC phrase requests → plain text	100%
cmpct	Ledger compaction	100%
edge	Multi-step / compound requests	100%
hand	Agent handoff / relay	88%
info	General facts → plain text	100%
irrel	Irrelevant / live queries → plain text	100%
know	Knowledge base search	100%
load	Session context loading	100%
pred	Factual / knowledge queries → plain text	100%
save	Session ledger save	92%
smem	Session memory search	92%
tran	Translation requests → plain text	100%

Eval: Ollama inference, temperature=0, Qwen3 thinking suppressed (<think>\n\n</think>), num_predict=160.
Gate: ≥90% = deploy.

Version History

Version	BFCL	Notes
v33	97.1%	Routing corpus v33, improved hand/save/smem
v32	97.1%	Routing corpus v32
v31	~96%	Routing corpus v31
v30	~95%	Baseline 14B routing

Tools

The model routes between exactly 6 tools:

session_load_context — load/fetch/resume project context
session_save_ledger — note/log/remember/record progress
session_save_handoff — handoff/relay to next agent/session
session_compact_ledger — compact/archive/shrink ledger
session_search_memory — recall past sessions/conversations
knowledge_search — search stored notes/knowledge base

Files

File	Size	Use
`prism-aac-14b-q4km.gguf`	9.3 GB	Recommended for Ollama

Cascade Role

Primary desktop tier. Handles ~97% of routing decisions locally.
Escalates to 32B for edge cases and multi-step compound requests.

Usage (Ollama)

ollama run dcostenco/prism-coder:14b

Training

Base: Qwen/Qwen3-14B (fp16, 14.8B params)
Framework: MLX-LM LoRA (rank=8, scale=20, 4 layers)
Merge: Direct safetensors manipulation (delta = scale/rank × B^T A^T)
Hardware: Apple Silicon (M-series, 64 GB RAM)

Downloads last month: 1,098

GGUF

Model size

15B params

Architecture

qwen3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for dcostenco/prism-coder-14b

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Quantized

(178)

this model

Quantizations

2 models