Instructions to use dcostenco/prism-coder-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dcostenco/prism-coder-8b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dcostenco/prism-coder-8b",
	filename="prism-aac-8b-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-8b 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-8b
# Run inference directly in the terminal:
llama-cli -hf dcostenco/prism-coder-8b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dcostenco/prism-coder-8b
# Run inference directly in the terminal:
llama-cli -hf dcostenco/prism-coder-8b

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-8b
# Run inference directly in the terminal:
./llama-cli -hf dcostenco/prism-coder-8b

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-8b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dcostenco/prism-coder-8b

Use Docker

docker model run hf.co/dcostenco/prism-coder-8b

LM Studio
Jan
Ollama
How to use dcostenco/prism-coder-8b with Ollama:
```
ollama run hf.co/dcostenco/prism-coder-8b
```

Unsloth Studio new

How to use dcostenco/prism-coder-8b 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-8b 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-8b 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-8b to start chatting

Pi new

How to use dcostenco/prism-coder-8b 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-8b

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-8b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dcostenco/prism-coder-8b 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-8b

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-8b

Run Hermes

hermes

Docker Model Runner
How to use dcostenco/prism-coder-8b with Docker Model Runner:
```
docker model run hf.co/dcostenco/prism-coder-8b
```

Lemonade

How to use dcostenco/prism-coder-8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dcostenco/prism-coder-8b

Run and chat with the model

lemonade run user.prism-coder-8b-{{QUANT_TAG}}

List all available models

lemonade list

prism-coder-8b / README.md

dcostenco

Upload README.md with huggingface_hub

9ae524d verified 12 days ago

preview code

raw

history blame contribute delete

3.18 kB

metadata

language: en
license: apache-2.0
tags:
  - tool-routing
  - function-calling
  - prism-aac
  - qwen3
  - gguf
base_model: Qwen/Qwen3-8B

prism-coder:8b — Tool Routing Model (iOS / Edge Tier)

Fine-tuned Qwen3-8B for 6-tool routing in the Prism AAC system. Primary deployment: iOS and edge devices via llama.cpp GGUF.

BFCL Routing Benchmark — v36 (Current)

Mean: 100.0% (3-seed average, seeds 2027/2028/2029, 102 cases each)

Category	Count	Description	Accuracy
aac	12	AAC phrase requests → plain text	100%
cmpct	6	Ledger compaction	100%
edge	6	Multi-step / compound requests	100%
hand	8	Agent handoff / relay	100%
info	5	General facts → plain text	100%
irrel	10	Irrelevant / live queries → plain text	100%
know	7	Knowledge base search	100%
load	9	Session context loading	100%
pred	8	Factual / knowledge queries → plain text	100%
save	13	Session ledger save	100%
smem	12	Session memory search	100%
tran	6	Translation requests → plain text	100%

Eval: MLX inference + thinking, temperature=0, 3-seed mean. Gate: ≥90% = deploy.

Cascade Benchmark (May 2026)

Full desktop cascade: 14b → 32b → Claude Opus (102 cases × 3 seeds)

Metric	Result
Cascade accuracy	100.0% (mean, 3 seeds)
Opus-solo etalon	98.3%
Δ vs Opus	+1.7%
Traffic served by 14b	99% (101/102 cases avg)
Traffic escalated to 32b	1% (1/102 avg)
Traffic reaching Opus API	0%

Fine-tuned cascade outperforms Claude Opus on edge (+16.7%) and know (+14.3%).

Version History

Version	BFCL	Notes
v36	100.0%	Fixed: smem "BFCL v4 notes" and "training loss" → session_search_memory
v35	98.0%	Proper safetensors merge — fixes mlx_lm.fuse LoRA loss
v32	98.0%	Routing corpus v32_8b, direct safetensors merge
v31	95.1%	Surgical smem/know boundary fix
v30	~93%	Baseline 8B routing

Tools

The model routes to exactly 6 tools:

Tool	Trigger
`session_load_context`	Load/resume project context
`session_save_ledger`	Note/log/record/remember something
`session_save_handoff`	Pass state to next agent/session
`session_compact_ledger`	Shrink/prune ledger (no relay)
`session_search_memory`	Recall prior session discussions
`knowledge_search`	Search stored knowledge base

Plain text (no tool) for: AAC phrases, translations, weather, general facts, code, math.

Model Details

Base: Qwen/Qwen3-8B
Format: GGUF Q4_K_M (~4.9 GB)
Context: 32,768 tokens
Training: MLX LoRA, rank=16, 16 layers, 1000 iters, LR=2e-6, v36 corpus (806 examples)
Merge: mlx_lm.fuse → llama.cpp convert → Q4_K_M quantization

Usage

ollama pull dcostenco/prism-coder-8b
ollama run prism-coder:8b

Or in the Prism Coder IDE — set model to prism-coder:8b in Settings.