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 19 days ago

Commit

2d696b2

verified ·

1 Parent(s): dd5c9f4

Update Model Card to Tals-coder-flash-02 with embedded Flash lightning GIF

Browse files

Files changed (1) hide show

README.md +20 -19

README.md CHANGED Viewed

@@ -21,15 +21,15 @@ pipeline_tag: text-generation
 <div align="center">
-# ⚡ Tals-coder-01 (27B Ternary + Grafted Native MTP + Multimodal Vision)
 ### *The Fastest 27B Coding Model on Consumer Hardware*
 <p align="center">
-  <img src="https://media.giphy.com/media/3oEjI6SIIHBdRxXI40/giphy.gif" width="520" alt="Usain Bolt Speed Meme" />
 </p>
-### *"Why wait 5 minutes for a reasoning model to finish an existential crisis in its chain-of-thought? Tals-coder-01 goes BRRRRR at 60 tok/s on a budget 16GB GPU."*
 </div>
@@ -39,20 +39,20 @@ pipeline_tag: text-generation
 On paper, an **NVIDIA RTX 4060 Ti 16GB** has a narrow 128-bit memory bus with **288 GB/s bandwidth**. Streaming an 8 GB 27B model on that bus physically caps standard autoregressive generation to **~25 tokens/sec**.
-**Tals-coder-01 shatters this barrier:**
 * ⚡ **55–60 tokens/second sustained** on RTX 4060 Ti 16GB (verified in production!).
 * 🚀 **Up to 76.7 tokens/second peak burst** during boilerplate and repetitive code blocks.
 * 💨 **120–150+ tokens/second projected** on high-bandwidth hardware (RTX 3090, 4090, A100).
-* 🎯 **Zero Overthinking:** No rambling monologues, no 2,000-token loops questioning itself. It cuts straight to the code.
 ---
 ## 🧬 Custom GGUF Quantization & Grafting
-**Tals-coder-01** is a custom GGUF quantization of **[prism-ml/Ternary-Bonsai-2-27B-gguf](https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf)**:
-* **Surgically Grafted Native MTP:** We permanently grafted the 65th Multi-Token Prediction (MTP) draft head and unrotated token embeddings directly into the main weights (`Tals-coder-01.gguf`). You do not need to juggle separate target and drafter model files—it's an **all-in-one standalone file** with native speculative decoding!
-* **Multimodal Vision Projector:** Includes the high-fidelity `Tals-coder-01-mmproj.gguf` CLIP Q8_0 vision tower (0.63 GB) for analyzing UI designs, charts, diagrams, and debugging screenshots.
 * **100% VRAM Execution:** Runs 27B parameters, 128,000 context, and multimodal vision completely on GPU (~13.8–14.1 GB / 16.0 GB total) with **zero CPU/PCIe spillover**.
 ---
@@ -64,8 +64,8 @@ Tested on **NVIDIA GeForce RTX 4060 Ti 16GB** (PCIe 4.0 x8, 288 GB/s bandwidth,
 | Configuration | Speculative Acceptance | Generation Speed | Context Window |
 | :--- | :---: | :---: | :---: |
 | **Base Model Only** (No MTP) | N/A (0%) | 24.8 – 25.8 tok/s | Up to 262k |
-| **Tals-coder-01 (MTP `n_max=1`)** | 77.8% | 40.7 – 42.5 tok/s | Up to 262k |
-| **Tals-coder-01 (MTP `n_max=2`)** *(Optimal)* | **68.9% – 74.2%** | **55.0 – 60.5 tok/s** | Up to 262k |
 | **Boilerplate / Code Bursts** | **85.2%** | **Up to 76.7 tok/s** | Up to 262k |
 | *Estimated RTX 4090 / 3090 (1,008 GB/s)* | *75% – 85%* | **120 – 155 tok/s** | *Full 262k* |
@@ -75,9 +75,10 @@ Tested on **NVIDIA GeForce RTX 4060 Ti 16GB** (PCIe 4.0 x8, 288 GB/s bandwidth,
 | Filename | Size | Description |
 | :--- | :---: | :--- |
-| `Tals-coder-01.gguf` | 8.25 GB | **Unified 27B Custom GGUF Quant** with Grafted Native MTP Head (All 65 layers). |
-| `Tals-coder-01-mmproj.gguf` | 0.63 GB | High-fidelity CLIP Q8_0 multimodal vision projector. |
 | `bonsai2-pascal.patch` | 259 KB | Source patch for custom Hadamard kernels & MTP timing. |
 ---
@@ -107,11 +108,11 @@ export CUDA_DEVICE_SCHEDULE=BLOCKING_SYNC
 ## ⚡ Recommended Run Configurations
 ### 1. Default Production Mode (128k Context + Grafted MTP + Vision)
-Optimal for coding in OpenCode, Cline, or Cursor on a 16GB GPU:
 ```bash
 ./llama-server \
-  -m "Tals-coder-01.gguf" \
-  --mmproj "Tals-coder-01-mmproj.gguf" \
   --mmproj-offload \
   --image-min-tokens 1024 \
   -ngl 99 \
@@ -128,8 +129,8 @@ Optimal for coding in OpenCode, Cline, or Cursor on a 16GB GPU:
 Maximum precision for complex mathematical derivations:
 ```bash
 ./llama-server \
-  -m "Tals-coder-01.gguf" \
-  --mmproj "Tals-coder-01-mmproj.gguf" \
   -ngl 99 \
   -c 65536 \
   -ctk f16 -ctv f16 \
@@ -142,7 +143,7 @@ Maximum precision for complex mathematical derivations:
 Process entire codebases and large book-length documents with zero CPU offload:
 ```bash
 ./llama-server \
-  -m "Tals-coder-01.gguf" \
   -ngl 99 \
   -c 262144 \
   -ctk q4_0 -ctv q4_0 \
@@ -157,7 +158,7 @@ Process entire codebases and large book-length documents with zero CPU offload:
 Set your tool's API endpoint to:
 * **Base URL:** `http://127.0.0.1:8080/v1`
-* **Model Name:** `tals-coder-01`
 * **API Key:** `not-needed` (any string)
 * **Temperature:** `0.0` – `0.2` (Deterministic coding & reasoning)

 <div align="center">
+# ⚡ Tals-coder-flash-02 (27B Ternary + Grafted Native MTP + Multimodal Vision)
 ### *The Fastest 27B Coding Model on Consumer Hardware*
 <p align="center">
+  <img src="flash.gif" width="600" alt="The Flash Lightning Speed" />
 </p>
+### *"Why wait 5 minutes for a reasoning model to finish an existential crisis in its chain-of-thought? Tals-coder-flash-02 goes at lightning speed with 60 tok/s on a budget 16GB GPU."*
 </div>
 On paper, an **NVIDIA RTX 4060 Ti 16GB** has a narrow 128-bit memory bus with **288 GB/s bandwidth**. Streaming an 8 GB 27B model on that bus physically caps standard autoregressive generation to **~25 tokens/sec**.
+**Tals-coder-flash-02 shatters this barrier:**
 * ⚡ **55–60 tokens/second sustained** on RTX 4060 Ti 16GB (verified in production!).
 * 🚀 **Up to 76.7 tokens/second peak burst** during boilerplate and repetitive code blocks.
 * 💨 **120–150+ tokens/second projected** on high-bandwidth hardware (RTX 3090, 4090, A100).
+* 🎯 **Zero Overthinking:** No rambling monologues, no 2,000-token loops questioning itself. It cuts straight to clean, functional code.
 ---
 ## 🧬 Custom GGUF Quantization & Grafting
+**Tals-coder-flash-02** is a custom GGUF quantization of **[prism-ml/Ternary-Bonsai-2-27B-gguf](https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf)**:
+* **Surgically Grafted Native MTP:** We permanently grafted the 65th Multi-Token Prediction (MTP) draft head and unrotated token embeddings directly into the main weights (`Tals-coder-flash-02.gguf`). You do not need to juggle separate target and drafter model files—it's an **all-in-one standalone file** with native speculative decoding!
+* **Multimodal Vision Projector:** Includes the high-fidelity `Tals-coder-flash-02-mmproj.gguf` CLIP Q8_0 vision tower (0.63 GB) for analyzing UI designs, charts, diagrams, and debugging screenshots.
 * **100% VRAM Execution:** Runs 27B parameters, 128,000 context, and multimodal vision completely on GPU (~13.8–14.1 GB / 16.0 GB total) with **zero CPU/PCIe spillover**.
 ---
 | Configuration | Speculative Acceptance | Generation Speed | Context Window |
 | :--- | :---: | :---: | :---: |
 | **Base Model Only** (No MTP) | N/A (0%) | 24.8 – 25.8 tok/s | Up to 262k |
+| **Tals-coder-flash-02 (MTP `n_max=1`)** | 77.8% | 40.7 – 42.5 tok/s | Up to 262k |
+| **Tals-coder-flash-02 (MTP `n_max=2`)** *(Optimal)* | **68.9% – 74.2%** | **55.0 – 60.5 tok/s** | Up to 262k |
 | **Boilerplate / Code Bursts** | **85.2%** | **Up to 76.7 tok/s** | Up to 262k |
 | *Estimated RTX 4090 / 3090 (1,008 GB/s)* | *75% – 85%* | **120 – 155 tok/s** | *Full 262k* |
 | Filename | Size | Description |
 | :--- | :---: | :--- |
+| `Tals-coder-flash-02.gguf` | 8.25 GB | **Unified 27B Custom GGUF Quant** with Grafted Native MTP Head (All 65 layers). |
+| `Tals-coder-flash-02-mmproj.gguf` | 0.63 GB | High-fidelity CLIP Q8_0 multimodal vision projector. |
 | `bonsai2-pascal.patch` | 259 KB | Source patch for custom Hadamard kernels & MTP timing. |
+| `flash.gif` | 5.05 MB | High-speed Flash badge visual asset. |
 ---
 ## ⚡ Recommended Run Configurations
 ### 1. Default Production Mode (128k Context + Grafted MTP + Vision)
+Run the single unified model with vision on a 16GB GPU:
 ```bash
 ./llama-server \
+  -m "Tals-coder-flash-02.gguf" \
+  --mmproj "Tals-coder-flash-02-mmproj.gguf" \
   --mmproj-offload \
   --image-min-tokens 1024 \
   -ngl 99 \
 Maximum precision for complex mathematical derivations:
 ```bash
 ./llama-server \
+  -m "Tals-coder-flash-02.gguf" \
+  --mmproj "Tals-coder-flash-02-mmproj.gguf" \
   -ngl 99 \
   -c 65536 \
   -ctk f16 -ctv f16 \
 Process entire codebases and large book-length documents with zero CPU offload:
 ```bash
 ./llama-server \
+  -m "Tals-coder-flash-02.gguf" \
   -ngl 99 \
   -c 262144 \
   -ctk q4_0 -ctv q4_0 \
 Set your tool's API endpoint to:
 * **Base URL:** `http://127.0.0.1:8080/v1`
+* **Model Name:** `tals-coder-flash-02`
 * **API Key:** `not-needed` (any string)
 * **Temperature:** `0.0` – `0.2` (Deterministic coding & reasoning)