Instructions to use AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 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 AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M

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 AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M

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 AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M

Use Docker

docker model run hf.co/AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M

LM Studio
Jan
Ollama
How to use AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 with Ollama:
```
ollama run hf.co/AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M
```

Unsloth Studio

How to use AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 to start chatting

How to use AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 with Docker Model Runner:
```
docker model run hf.co/AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M
```

Lemonade

How to use AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M

Run and chat with the model

lemonade run user.NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M

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 AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M

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 "AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16:Q4_K_M" \
  --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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Released as part of the NOESIS Professional Multilingual Dubbing Automation Platform (framework: DHCF-FNO — Deterministic Hybrid Control Framework for Frozen Neural Operators).

Founder: Ilia Bolotnikov
Organization: AMAImedia.com
X (Twitter): @AMAImediacom
LinkedIn: Ilia Bolotnikov
Telegram: @djbionicl
NOESIS version: v16.1
Release date: 2026-08

Qwopus3.5-9B-PromptEng-v3.5-BF16

Role: Prompt-engineering / instruction-shaping specialist (9B dense, Qwopus3.5-v3.5 family). BF16-only locally (4-shard safetensors; no GGUF). Think-model — use closed-think prefill (<think>\n\n</think>\n\n) for deterministic non-reasoning output.

Test results (2026-06-17)

No NOESIS-pipeline eval has been run on this model — it is off-role for the dubbing suite (Director / Inspector / LongCtx-Supervisor / Translate). Running supervisor-12 or FLORES on a prompt-engineering model would be uninformative (wrong task), so no fabricated numbers are recorded here.

Local constraint: BF16 ≈ 18 GB → does not fit the RTX 3060 6 GB GPU without quantization, so tokens/sec was not measured. A cross-role benchmark would first require a GGUF/NF4 build.

NOESIS dubbing models (for context — measured 2026-06-17)

Model	Role	Score
NOESIS-0.8B-Director	orchestration	10/10 (grammar)
NOESIS-0.8B-Inspector	per-stage QC	15/16 (grammar)
NOESIS-4B-LongCtx-Supervisor	long-ctx QC	11/12 (grammar); translate chrF++ 41.7
Qwopus3.5-9B-Translate	translation	chrF++ 43.8 / BLEU 16.5 (FLORES n=20)

If you want this model benchmarked on a specific task, say which and provide/allow a GGUF or NF4 build.

Downloads last month: 123

Safetensors

Model size

9B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including AMAImedia/NOESIS-Qwopus3.5-9B-PromptEng-v3.5-BF16

NOESIS-Original-Trained-Models

Collection

18 items • Updated 2 days ago