Instructions to use Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2 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 Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2
# Run inference directly in the terminal:
llama cli -hf Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2
# Run inference directly in the terminal:
llama cli -hf Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2

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 Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2
# Run inference directly in the terminal:
./llama-cli -hf Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2

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 Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2

Use Docker

docker model run hf.co/Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2

LM Studio
Jan
Ollama
How to use Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2 with Ollama:
```
ollama run hf.co/Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2
```
Unsloth Desktop

How to use Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2

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": "Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2 with Docker Model Runner:
```
docker model run hf.co/Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2
```

Lemonade

How to use Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2

Run and chat with the model

lemonade run user.Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2

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 Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2

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 "Fredred89/Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2" \
  --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"

Qwopus3.6-27B-Coder-GGUF-Predator-Q-ASI-v2 / recipe.txt

Fredred89

Upload recipe.txt with huggingface_hub

bd45698 verified 3 months ago

Raw History Blame Contribute Delete

1.9 kB

	<![CDATA[
	# MoQ-4.0-AttnQSelectiveEdgeNL recipe (regex anchored)

	# embeddings / logits
	^token_embd\.weight$=Q4_K
	^output\.weight$=bf16
	^output_norm\.weight$=bf16

	# FFN: down/gate are high elasticity -> IQ3_S
	^blk\.\d+\.ffn_down\.weight$=IQ3_S
	^blk\.\d+\.ffn_gate\.weight$=IQ3_S

	# FFN up: edge layers promoted, rest IQ4_XS
	^blk\.(?:0\|1\|2\|3\|60\|61\|62\|63)\.ffn_up\.weight$=IQ4_NL
	^blk\.(?:[4-9]\|[1-5][0-9])\.ffn_up\.weight$=IQ4_XS

	# SSM layers (non-attention blocks) keep IQ4_XS
	^blk\.(?:0\|1\|2\|4\|5\|6\|8\|9\|10\|12\|13\|14\|16\|17\|18\|20\|21\|22\|24\|25\|26\|28\|29\|30\|32\|33\|34\|36\|37\|38\|40\|41\|42\|44\|45\|46\|48\|49\|50\|52\|53\|54\|56\|57\|58\|60\|61\|62)\.attn_qkv\.weight$=IQ4_XS
	^blk\.(?:0\|1\|2\|4\|5\|6\|8\|9\|10\|12\|13\|14\|16\|17\|18\|20\|21\|22\|24\|25\|26\|28\|29\|30\|32\|33\|34\|36\|37\|38\|40\|41\|42\|44\|45\|46\|48\|49\|50\|52\|53\|54\|56\|57\|58\|60\|61\|62)\.attn_gate\.weight$=IQ4_XS
	^blk\.(?:0\|1\|2\|4\|5\|6\|8\|9\|10\|12\|13\|14\|16\|17\|18\|20\|21\|22\|24\|25\|26\|28\|29\|30\|32\|33\|34\|36\|37\|38\|40\|41\|42\|44\|45\|46\|48\|49\|50\|52\|53\|54\|56\|57\|58\|60\|61\|62)\.ssm_out\.weight$=IQ4_XS

	# Full-attention layers every 4th:
	# selective upgrade for edge layers, mid layers stay IQ4_XS
	^blk\.(?:3\|7\|11\|59\|63)\.attn_q\.weight$=IQ4_NL
	^blk\.(?:15\|19\|23\|27\|31\|35\|39\|43\|47\|51\|55)\.attn_q\.weight$=IQ4_XS
	^blk\.(?:3\|7\|11\|15\|19\|23\|27\|31\|35\|39\|43\|47\|51\|55\|59\|63)\.attn_k\.weight$=bf16
	^blk\.(?:3\|7\|11\|15\|19\|23\|27\|31\|35\|39\|43\|47\|51\|55\|59\|63)\.attn_v\.weight$=bf16

	# Attention output: protect edges
	^blk\.(?:3\|63)\.attn_output\.weight$=Q6_K
	^blk\.(?:7\|11\|15\|19\|23\|27\|31\|35\|39\|43\|47\|51\|55\|59)\.attn_output\.weight$=Q5_K

	# Norms and SSM params in bf16
	^blk\.\d+\.attn_norm\.weight$=bf16
	^blk\.\d+\.post_attention_norm\.weight$=bf16
	^blk\.\d+\.ssm_norm\.weight$=bf16
	^blk\.\d+\.attn_k_norm\.weight$=bf16
	^blk\.\d+\.attn_q_norm\.weight$=bf16
	^blk\.\d+\.ssm_a$=bf16
	^blk\.\d+\.ssm_conv1d\.weight$=bf16
	^blk\.\d+\.ssm_dt\.bias$=bf16
	^blk\.\d+\.ssm_alpha\.weight$=bf16
	^blk\.\d+\.ssm_beta\.weight$=bf16
	]]>