Instructions to use talxcc/Tals-coder-flash-01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use talxcc/Tals-coder-flash-01 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 talxcc/Tals-coder-flash-01
# Run inference directly in the terminal:
llama cli -hf talxcc/Tals-coder-flash-01

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf talxcc/Tals-coder-flash-01
# Run inference directly in the terminal:
llama cli -hf talxcc/Tals-coder-flash-01

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 talxcc/Tals-coder-flash-01
# Run inference directly in the terminal:
./llama-cli -hf talxcc/Tals-coder-flash-01

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 talxcc/Tals-coder-flash-01
# Run inference directly in the terminal:
./build/bin/llama-cli -hf talxcc/Tals-coder-flash-01

Use Docker

docker model run hf.co/talxcc/Tals-coder-flash-01

LM Studio
Jan

vLLM

How to use talxcc/Tals-coder-flash-01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "talxcc/Tals-coder-flash-01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "talxcc/Tals-coder-flash-01",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/talxcc/Tals-coder-flash-01

Ollama
How to use talxcc/Tals-coder-flash-01 with Ollama:
```
ollama run hf.co/talxcc/Tals-coder-flash-01
```
Unsloth Desktop

How to use talxcc/Tals-coder-flash-01 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf talxcc/Tals-coder-flash-01

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": "talxcc/Tals-coder-flash-01"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use talxcc/Tals-coder-flash-01 with Docker Model Runner:
```
docker model run hf.co/talxcc/Tals-coder-flash-01
```

Lemonade

How to use talxcc/Tals-coder-flash-01 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull talxcc/Tals-coder-flash-01

Run and chat with the model

lemonade run user.Tals-coder-flash-01-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use talxcc/Tals-coder-flash-01 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf talxcc/Tals-coder-flash-01

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 talxcc/Tals-coder-flash-01

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use talxcc/Tals-coder-flash-01 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf talxcc/Tals-coder-flash-01

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 "talxcc/Tals-coder-flash-01" \
  --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"

talxcc commited on 22 days ago

Commit

fe60d81

verified ·

1 Parent(s): ff78187

Update model lineage: PrismML -> Swift-Bonsai -> Tals-coder-01 (Custom Graft)

Browse files

Files changed (1) hide show

README.md +30 -13

README.md CHANGED Viewed

@@ -15,31 +15,49 @@ tags:
 - reasoning
 - agentic
 base_model:
 - ukisai/Swift-Bonsai-2-GGUF
 - killy369/Ternary-Bonsai-2-27B-MTP-drafter-GGUF
 license: apache-2.0
 pipeline_tag: text-generation
 ---
-# ⚡ Tals-coder-01 (Custom GGUF Quant: Ternary Bonsai 2 + Grafted Native MTP)
-**Tals-coder-01** is a custom GGUF quantization and architectural graft of **Ternary Bonsai 2 (27B)**. Engineered specifically for consumer 16GB VRAM GPUs (RTX 4060 Ti 16GB, RTX 4070 Ti Super, RTX 4080/4090), it delivers **55–60 tokens/second** on a budget 128-bit memory bus (288 GB/s), scaling to **120–150+ tokens/second** on high-bandwidth hardware (RTX 3090, 4090, A100).
 ---
-## 🧬 Architectural Pedigree & Custom GGUF Quantization
-This model is a custom GGUF quant built upon and fused from:
-1. **Base Model:** Based on **[Swift-Bonsai-2-PQ2_0.gguf](https://huggingface.co/ukisai/Swift-Bonsai-2-GGUF)** by Ukisai — a 27B parameter Ternary model using Walsh-Hadamard rotation representation (`PQ2_0` 142 quantization).
-2. **Native MTP Drafter:** Integrated with weights from **[Ternary-Bonsai-2-27B-MTP-drafter-GGUF](https://huggingface.co/killy369/Ternary-Bonsai-2-27B-MTP-drafter-GGUF)** by killy369 — featuring a 1-layer native Multi-Token Prediction (MTP) draft head with a 64k pruned vocabulary.
-3. **The Custom Graft:** Rather than requiring users to configure and orchestrate separate target and draft models (`-m` and `-md`), **Tals-coder-01 grafts the 65th MTP layer and unrotated token embeddings directly into the core GGUF file** (`Tals-coder-01.gguf`), producing an all-in-one standalone model.
-4. **Multimodal Vision:** Paired with **`Tals-coder-01-mmproj.gguf`** (0.63 GB CLIP Q8_0 vision tower) for full image comprehension, UI analysis, and diagram inspection.
 ---
 ## 🌟 Why Tals-coder-01?
-* **All-in-One Model File:** The native MTP draft head is built directly into `Tals-coder-01.gguf` (`qwen35.nextn_predict_layers = 1`, `qwen35.block_count = 65`).
 * **Pruned Reasoning (No Overthinking):** Unlike verbose models that get trapped in endless monologue loops, Tals-coder-01 outputs direct, clean, and immediately functional code.
 * **55–60 tok/s on Budget 16GB Cards:** Breaks through the theoretical memory bandwidth barrier with verified **68%–85% MTP speculative draft acceptance**.
 * **100% VRAM Execution:** Runs 27B parameters, 128k context, and vision completely on GPU (~13.8–14.1 GB / 16.0 GB total) with **zero CPU/PCIe RAM spillover**.
@@ -158,10 +176,9 @@ Set your tool's API endpoint to:
 ## 🙏 Credits & Acknowledgements
-Special thanks to the open-source creators whose foundational work made this custom GGUF quant distribution possible:
-* **[Ukisai](https://huggingface.co/ukisai/Swift-Bonsai-2-GGUF):** Creator of the original **Swift-Bonsai-2-PQ2_0.gguf** (Ternary Bonsai 2) model weights and quantization basis.
-* **[killy369 / Kilian](https://huggingface.co/killy369/Ternary-Bonsai-2-27B-MTP-drafter-GGUF):** Creator of the **Ternary-Bonsai-2-27B-MTP-drafter-GGUF** native draft weights and pruned 64k vocabulary.
-* **[Prism ML / Pascal](https://github.com/prism-ml):** For pioneering ternary Hadamard kernels and custom llama.cpp acceleration.
 * **Qwen Team:** For the underlying Qwen 3.5 architecture.
 Distributed under the **Apache 2.0** license.

 - reasoning
 - agentic
 base_model:
+- prism-ml/Ternary-Bonsai-2-27B-gguf
 - ukisai/Swift-Bonsai-2-GGUF
 - killy369/Ternary-Bonsai-2-27B-MTP-drafter-GGUF
 license: apache-2.0
 pipeline_tag: text-generation
 ---
+# ⚡ Tals-coder-01 (Custom GGUF Quant: PrismML → Swift-Bonsai → Grafted MTP)
+**Tals-coder-01** is a custom GGUF quantization and architectural graft engineered for high-throughput coding on consumer 16GB VRAM GPUs (RTX 4060 Ti 16GB, RTX 4070 Ti Super, RTX 4080/4090). It delivers **55–60 tokens/second** on a budget 128-bit memory bus (288 GB/s), scaling to **120–150+ tokens/second** on high-bandwidth hardware (RTX 3090, 4090, A100).
 ---
+## 🧬 Architectural Lineage & Evolution
+The lineage of this model follows a direct three-tier evolution:
+```
+[1. Base Foundation]  PrismML / Ternary-Bonsai-2-27B
+          │           (Original Ternary {-1,0,+1} Walsh-Hadamard Architecture)
+          ▼
+[2. Adaptation]       Ukisai / Swift-Bonsai-2-GGUF
+          │           (High-performance ternary PQ2_0 quantization)
+          ▼
+[3. Custom Graft]     talxcc / Tals-coder-01 (Our Model)
+                      (Surgically grafts native MTP Drafter by killy369 into a single
+                       unified GGUF file + Q8_0 Multimodal Vision + Pruned Reasoning)
+```
+1. **Base Foundation — [PrismML](https://huggingface.co/prism-ml):**
+   The foundational architecture originates from **[prism-ml/Ternary-Bonsai-2-27B-gguf](https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf)**, the pioneer of 1.58-bit ternary {-1, 0, +1} neural weights and custom Walsh-Hadamard rotation kernels.
+2. **Intermediate Quant — [Ukisai](https://huggingface.co/ukisai/Swift-Bonsai-2-GGUF):**
+   Built upon **[Swift-Bonsai-2-PQ2_0.gguf](https://huggingface.co/ukisai/Swift-Bonsai-2-GGUF)**, which refined the ternary base weights for high-speed inference.
+3. **MTP Speculative Drafter — [killy369 / Kilian](https://huggingface.co/killy369/Ternary-Bonsai-2-27B-MTP-drafter-GGUF):**
+   Utilizes the trained 1-layer native Multi-Token Prediction (MTP) draft head weights and pruned 64k vocabulary from **[Ternary-Bonsai-2-27B-MTP-drafter-GGUF](https://huggingface.co/killy369/Ternary-Bonsai-2-27B-MTP-drafter-GGUF)**.
+4. **Our Custom GGUF Quant & Graft — Tals-coder-01:**
+   Rather than requiring users to manually run and orchestrate separate target and draft models (`-m` and `-md`), **Tals-coder-01 fuses the 65th MTP draft layer and unrotated token embeddings directly into the core GGUF file (`Tals-coder-01.gguf`)**. This creates a single all-in-one model with pruned, non-overthinking reasoning and native CLIP Q8_0 multimodal vision (`Tals-coder-01-mmproj.gguf`).
 ---
 ## 🌟 Why Tals-coder-01?
+* **Single-File Grafted MTP:** The native MTP draft head is built directly into `Tals-coder-01.gguf` (`qwen35.nextn_predict_layers = 1`, `qwen35.block_count = 65`).
 * **Pruned Reasoning (No Overthinking):** Unlike verbose models that get trapped in endless monologue loops, Tals-coder-01 outputs direct, clean, and immediately functional code.
 * **55–60 tok/s on Budget 16GB Cards:** Breaks through the theoretical memory bandwidth barrier with verified **68%–85% MTP speculative draft acceptance**.
 * **100% VRAM Execution:** Runs 27B parameters, 128k context, and vision completely on GPU (~13.8–14.1 GB / 16.0 GB total) with **zero CPU/PCIe RAM spillover**.
 ## 🙏 Credits & Acknowledgements
+* **[PrismML](https://huggingface.co/prism-ml):** The original creators of the **Ternary-Bonsai-2-27B** architecture and pioneering Hadamard quantization kernels.
+* **[Ukisai](https://huggingface.co/ukisai/Swift-Bonsai-2-GGUF):** For **Swift-Bonsai-2**, adapting and quantizing the ternary base weights.
+* **[killy369 / Kilian](https://huggingface.co/killy369/Ternary-Bonsai-2-27B-MTP-drafter-GGUF):** For creating the **Ternary-Bonsai-2-27B-MTP-drafter-GGUF** native draft weights and pruned 64k vocabulary.
 * **Qwen Team:** For the underlying Qwen 3.5 architecture.
 Distributed under the **Apache 2.0** license.