Instructions to use prism-ml/Ternary-Bonsai-27B-mlx-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prism-ml/Ternary-Bonsai-27B-mlx-2bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("prism-ml/Ternary-Bonsai-27B-mlx-2bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use prism-ml/Ternary-Bonsai-27B-mlx-2bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "prism-ml/Ternary-Bonsai-27B-mlx-2bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "prism-ml/Ternary-Bonsai-27B-mlx-2bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use prism-ml/Ternary-Bonsai-27B-mlx-2bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "prism-ml/Ternary-Bonsai-27B-mlx-2bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "prism-ml/Ternary-Bonsai-27B-mlx-2bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "prism-ml/Ternary-Bonsai-27B-mlx-2bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use prism-ml/Ternary-Bonsai-27B-mlx-2bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "prism-ml/Ternary-Bonsai-27B-mlx-2bit"

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 prism-ml/Ternary-Bonsai-27B-mlx-2bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prism-ml/Ternary-Bonsai-27B-mlx-2bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "prism-ml/Ternary-Bonsai-27B-mlx-2bit"

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 "prism-ml/Ternary-Bonsai-27B-mlx-2bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

poor coding performance, 5/13 pass only

by cloudyu - opened Jul 20

Discussion

cloudyu

Jul 20

========================================================================
BENCHMARK RESULTS | 2026-07-20 08:19

ID Title Verdict KW% Time Tok/s

math_02 Euler Totient Sum — last 6 di [ERROR] 100% 131.6s 21
math_03 Lattice Paths Avoiding the An [ERROR] 67% 175.4s 21
math_04 Segmented Sieve in [10^12, 10 [PASS] 100% 130.7s 23
code_01 Median of Two Sorted Arrays — [PASS] 100% 157.2s 19
code_02 Thread-Safe LRU Cache with TT [PASS] 100% 199.5s 21
code_03 Persistent Segment Tree — K-t [FAIL] 67% 221.4s 23
code_04 Multi-Head Attention + RoPE ( [ERROR] 100% 221.1s 17
code_05 Dijkstra vs A* on Geometric G [ERROR] 100% 175.7s 21
logic_01 Knights & Knaves — Exhaustive [ERROR] 100% 130.9s 23
logic_02 Verify Three Mathematical Cla [PASS] 100% 127.8s 22
sci_01 Figure-8 Three-Body Orbit — E [PASS] 100% 116.8s 19
sci_02 Metropolis-Hastings vs HMC Co [ERROR] 100% 222.1s 19
sci_03 Optimizer Comparison on Rosen [FAIL] 100% 175.9s 19

PASS: 5/13 | Total: 2186s | Avg KW: 94.9%

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

poor coding performance, 5/13 pass only

======================================================================== BENCHMARK RESULTS | 2026-07-20 08:19

PASS: 5/13 | Total: 2186s | Avg KW: 94.9%

========================================================================
BENCHMARK RESULTS | 2026-07-20 08:19