Instructions to use Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark 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 Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0
# Run inference directly in the terminal:
llama cli -hf Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0
# Run inference directly in the terminal:
llama cli -hf Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0

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 Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0
# Run inference directly in the terminal:
./llama-cli -hf Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0

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 Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0

Use Docker

docker model run hf.co/Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0

LM Studio
Jan

vLLM

How to use Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0

Ollama
How to use Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark with Ollama:
```
ollama run hf.co/Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0
```
Unsloth Desktop

How to use Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_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": "Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark with Docker Model Runner:
```
docker model run hf.co/Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0
```

Lemonade

How to use Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0

Run and chat with the model

lemonade run user.Bonsai-27B-antidoom-1bit-DSpark-Q1_0

List all available models

lemonade list

Hermes Agent

How to use Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_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 Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_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 "Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark:Q1_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"

Danny-Dasilva commited on Jul 15

Commit

f9172f5

verified ·

1 Parent(s): f209f08

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +34 -10

README.md CHANGED Viewed

@@ -44,17 +44,41 @@ build/bin/llama-server \
   -ngl 999 -ngld 999 -fa on -c 16384 -np 1
 ```
-## Benchmark (RTX 5090, greedy, bs=1, 256 tok)
-| Config | tok/s | accept | note |
-|---|---|---|---|
-| **DSpark, code prompt** | **186.2** | 78.6% | **1.16× over native** |
-| Native (llama-bench tg256) | 161.2 | — | reference |
-| Native (llama-server decode) | 157.5 | — | |
-| DSpark, prose prompt | 132.8 | 51% | low-accept workloads slower |
-DSpark speedup is workload-dependent: on predictable content (code, high accept) it beats native;
-the 1-bit target is so bandwidth-cheap (3.5 GB) that low-accept drafting overhead can dominate.
-The 5090 exceeds prism-ml's published H100 native (104.8 t/s) — this 1-bit model is memory-bandwidth-bound.
 ## Antidoom (FTPO) pass — what was done
 Bonsai-27B is unusually **doom-loop resistant** (it self-corrects repetition and stays coherent even

   -ngl 999 -ngld 999 -fa on -c 16384 -np 1
 ```
+## Speed comparison — all four models (RTX 5090, 32 GB)
+Single stream, greedy, 256 new tokens, PrismML llama.cpp fork (CUDA 13 / sm_120).
+Native = `llama-bench` tg256 (fa=1, r=2). DSpark = `llama-speculative-simple`,
+`--spec-draft-n-max 4`, code prompt (high-acceptance workload); all four runs measured
+back-to-back in the same session.
+| Model | Native tok/s | + DSpark tok/s | Accept | DSpark speedup |
+|---|---:|---:|---:|---:|
+| Bonsai-27B **1-bit** (base) | 166.0 | **208.3** | 78.6% | 1.25× |
+| **Bonsai-27B 1-bit antidoom** (this family) | 153.7 | **192.4** | 74.6% | 1.25× |
+| Ternary-Bonsai-27B (base) | 136.5 | **185.9** | 69.2% | 1.36× |
+| **Ternary-Bonsai-27B antidoom** (this family) | 129.2 | **184.6** | 69.2% | 1.43× |
+```
+tok/s (code prompt, bs=1)                 native ▒   +DSpark █
+Bonsai 1-bit base      ▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 166.0
+                       ████████████████████████████████ 208.3
+Bonsai 1-bit antidoom  ▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 153.7
+                       █████████████████████████████ 192.4
+Ternary base           ▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 136.5
+                       ████████████████████████████ 185.9
+Ternary antidoom       ▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 129.2
+                       ████████████████████████████ 184.6
+```
+Notes:
+- DSpark's gain is workload-dependent: on low-acceptance prose (~51%) the 1-bit target can be
+  *slower* than native because the tiny weights make drafting overhead relatively expensive.
+- The antidoom variants are ~5–8% slower natively because re-quantization stored the output
+  tensor at q6_K (prism's originals pack it smaller); with DSpark the gap mostly closes.
+- FTPO does not hurt the DSpark drafter (accept 74.6–78.6% 1-bit, 69.2% ternary, unchanged
+  base vs antidoom for ternary).
+- All numbers beat prism-ml's published H100 figures (104.8→143.8 1-bit, 98.0→131.8 ternary):
+  these models are memory-bandwidth-bound and the 5090 has more bandwidth headroom at bs=1.
 ## Antidoom (FTPO) pass — what was done
 Bonsai-27B is unusually **doom-loop resistant** (it self-corrects repetition and stays coherent even