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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use prism-ml/Ternary-Bonsai-2-27B-gguf 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 prism-ml/Ternary-Bonsai-2-27B-gguf:F16
# Run inference directly in the terminal:
llama cli -hf prism-ml/Ternary-Bonsai-2-27B-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prism-ml/Ternary-Bonsai-2-27B-gguf:F16
# Run inference directly in the terminal:
llama cli -hf prism-ml/Ternary-Bonsai-2-27B-gguf:F16

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 prism-ml/Ternary-Bonsai-2-27B-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf prism-ml/Ternary-Bonsai-2-27B-gguf:F16

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 prism-ml/Ternary-Bonsai-2-27B-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prism-ml/Ternary-Bonsai-2-27B-gguf:F16

Use Docker

docker model run hf.co/prism-ml/Ternary-Bonsai-2-27B-gguf:F16

LM Studio
Jan

vLLM

How to use prism-ml/Ternary-Bonsai-2-27B-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prism-ml/Ternary-Bonsai-2-27B-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prism-ml/Ternary-Bonsai-2-27B-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prism-ml/Ternary-Bonsai-2-27B-gguf:F16

Ollama
How to use prism-ml/Ternary-Bonsai-2-27B-gguf with Ollama:
```
ollama run hf.co/prism-ml/Ternary-Bonsai-2-27B-gguf:F16
```
Unsloth Desktop

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prism-ml/Ternary-Bonsai-2-27B-gguf:F16

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": "prism-ml/Ternary-Bonsai-2-27B-gguf:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prism-ml/Ternary-Bonsai-2-27B-gguf with Docker Model Runner:
```
docker model run hf.co/prism-ml/Ternary-Bonsai-2-27B-gguf:F16
```

Lemonade

How to use prism-ml/Ternary-Bonsai-2-27B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prism-ml/Ternary-Bonsai-2-27B-gguf:F16

Run and chat with the model

lemonade run user.Ternary-Bonsai-2-27B-gguf-F16

List all available models

lemonade list

Hermes Agent

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prism-ml/Ternary-Bonsai-2-27B-gguf:F16

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-2-27B-gguf:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prism-ml/Ternary-Bonsai-2-27B-gguf:F16

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-2-27B-gguf:F16" \
  --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"

New discussion

Resources

View closed (11)

−2 logit bias on PTQ1_0, RTX 5060 Laptop: MATH-500 44/50 → 43/50

#83 opened 2 days ago by

7dollarbooks

Add RTX 3080 (10 GB) to the cross-platform throughput table

#82 opened 2 days ago by

Siphion

Works on Tesla V100-16GB (SM 7.0): 52 tok/s @ 64K context

#81 opened 3 days ago by

Vyach59

nobody told us, but Pelikan can be ANIMATEEED!

#80 opened 3 days ago by

KottCh

could gemma4-31B-it be better?

👍 1

#79 opened 5 days ago by

luckystar199746

Intel Arc: a faster SYCL path for PTQ1_0 (about 88 t/s with MTP on a B580)

#78 opened 5 days ago by

torchit1

Sitting frozen like a nuclear bomb, the 8G laptop speeds up from 50 tokens straight to 70 tokens，8G再次从50Token/S大幅升到恐怖的70Token/s

#75 opened 6 days ago by

SuperLogic

I made a ternary 35B-A3B based on the results of my previous Bonsai-2 forensics & research work.

🔥 4

#74 opened 7 days ago by

SkyIsNotGreen

Think too much

#73 opened 7 days ago by

jezzza1401

Which Jinja Template?

#70 opened 9 days ago by

Omnomynous

image to SVG test: Ichigo :)

🔥 3

#69 opened 9 days ago by

KottCh

Does not work in LM Studio (NB - update CUDA, use NOXZURE1's answer)

#68 opened 9 days ago by

SoulFireMage

Memory performance

👀 1

#67 opened 9 days ago by

trombonator

One 27B model, two jobs — chat:50token/s + JEV decision engine:0.5s — on an 8 GB laptop

🧠 3

#65 opened 10 days ago by

SuperLogic

Can you create Ternary versions for 35b-a3b models?

#64 opened 10 days ago by

naildirect

Pull coding capability, the Tetris.html which Bonsai-2-27b generated cannot play - console error

#63 opened 10 days ago by

mind0n

I took Bonsai 2 27B apart, part 2: the format is public, the last 8% is ordinary ternary QAT.

👀 1

#62 opened 10 days ago by

SkyIsNotGreen

Set the model name and min_p in the GGUF metadata (weights unchanged)

👍 1

#59 opened 11 days ago by

bri-prism

for 16gb vram context size <=114688 is fast. Pelican is gorgeous :)

👍🤯 4

#56 opened 11 days ago by

KottCh

intel alchemist kernel

#55 opened 11 days ago by

Demilenos

Real KLD testing against Unsloth's gguf BF16 of Qwen 3.8-27B

👀👍 3

#54 opened 11 days ago by

mrumel

When will they release the official version with ROCM or Vulkan support for the 6900XT?

#53 opened 12 days ago by

aidoluiz

AMD works just wonderfully, here is how:

#52 opened 12 days ago by

RegisteredWednesday

issue : 6800 (rdna 2) gpu card on PrismML-Eng llama.cpp . cant run model by unsloth Studio and ..

👍 1

#51 opened 12 days ago by

myhugginfacegacc

SYCL backend: any speculative type collapses performance (even target prefill drops ~200x) - draft model itself is healthy

#50 opened 13 days ago by

Yoo00ooOO

How does the 2080 Ti 22G perform with this model?

#49 opened 13 days ago by

coresen

PLEASE stop lying about the "intelligence" of the model.

🔥👍 24

#47 opened 13 days ago by

Splarkszter

在4060笔记本，8G下，优化到45Token/S之后，再提10%到50Token/S，但这还不是上限...理论上限可能高达65Token/S

👍 2

#46 opened 14 days ago by

SuperLogic

Solved "xhigh" loop and include MTP. Test on 4080 12G VRAM laptop, reach ~60 t/s

👍🚀 3

#45 opened 14 days ago by

zhijin123

Built a multi agent orchestrator with it

🚀 2

#43 opened 14 days ago by

anubhav200

dspark will improve intelligence/bit

#42 opened 14 days ago by

john1248

3060 rtx 8 gb vram here ... share your preset !

#41 opened 14 days ago by

oytaub

First time used... Failed basic tool calls immediately. (Q2 variant)

👍 5

#40 opened 14 days ago by

laser50

在4060笔记本，8G下，优化到45Token/S，已经达到大厂的Token接口速度，彻底实现Token自由，大家再也不需要去大厂订阅。

#39 opened 14 days ago by

SuperLogic

Ternary-Bonsai-2-27B on an RTX 2060 SUPER 8GB — Japanese supplied-context reasoning is the biggest surprise

#38 opened 14 days ago by

mktnhr

LM Studio says no

#37 opened 14 days ago by

Vort

No sure why all the hate?

❤️ 2

#36 opened 15 days ago by

Mogsie

It is fighting with the harness, chat template and blaming the human operator

#35 opened 15 days ago by

gbuzhf

OMG

#34 opened 15 days ago by

darkmatter2222

Density table divides Bonsai by the ideal 5.80 GB; competitors by shipped files

#33 opened 15 days ago by

makerportal

NB啊

#32 opened 15 days ago by

lpiao3825

Really useful quantified small models PQ2_0. Have good intelligence and pretty fast. (With evalscope testing result)

🧠🚀 4

#31 opened 15 days ago by

zhijin123

confused on sampling parameters

👀 1

#30 opened 15 days ago by

Jcamacho05

Bonsai 2 27B Uncensored

#29 opened 15 days ago by

e-RHM-e

Joining your group

#28 opened 15 days ago by

Mohammedkarimi

Surprisingly good PTQ1_0 quantization – and ~39.5 tok/s on an RTX 4070

👍🔥 7

#27 opened 15 days ago by

TheWegemann

出一个Q6的试试？看看能力能不能保留FP16的99.99%？

#26 opened 15 days ago by

kelei999999

Update README.md

#25 opened 15 days ago by

rikunarita-3

Something is wrong

#24 opened 16 days ago by

kashish4u

In-file MTP speculation refused on Hadamard-folded weights (prism-b10683); ~1.34x decode after the 7-line embedding fix

#23 opened 16 days ago by

zhaokeqi