Instructions to use baa-ai/Qwen3.8-27B-RAM-13GB-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use baa-ai/Qwen3.8-27B-RAM-13GB-GGUF 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 baa-ai/Qwen3.8-27B-RAM-13GB-GGUF
# Run inference directly in the terminal:
llama cli -hf baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf baa-ai/Qwen3.8-27B-RAM-13GB-GGUF
# Run inference directly in the terminal:
llama cli -hf baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf baa-ai/Qwen3.8-27B-RAM-13GB-GGUF
# Run inference directly in the terminal:
./build/bin/llama cli -hf baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

Use Docker

docker model run hf.co/baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

Llama new
LM Studio
Jan

vLLM

How to use baa-ai/Qwen3.8-27B-RAM-13GB-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "baa-ai/Qwen3.8-27B-RAM-13GB-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "baa-ai/Qwen3.8-27B-RAM-13GB-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

Ollama
How to use baa-ai/Qwen3.8-27B-RAM-13GB-GGUF with Ollama:
```
ollama run hf.co/baa-ai/Qwen3.8-27B-RAM-13GB-GGUF
```
Unsloth Desktop

How to use baa-ai/Qwen3.8-27B-RAM-13GB-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

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": "baa-ai/Qwen3.8-27B-RAM-13GB-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use baa-ai/Qwen3.8-27B-RAM-13GB-GGUF with Docker Model Runner:
```
docker model run hf.co/baa-ai/Qwen3.8-27B-RAM-13GB-GGUF
```

Lemonade

How to use baa-ai/Qwen3.8-27B-RAM-13GB-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

Run and chat with the model

lemonade run user.Qwen3.8-27B-RAM-13GB-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use baa-ai/Qwen3.8-27B-RAM-13GB-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

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 baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use baa-ai/Qwen3.8-27B-RAM-13GB-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

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 "baa-ai/Qwen3.8-27B-RAM-13GB-GGUF" \
  --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"

Qwen3.8-27B — 13GB (GGUF)

GGUF build of Qwen/Qwen3.8-27B, capability-validated by baa.ai for faithful, retrieval-grounded reading — a full 27B reader that runs on a single 16 GB GPU (e.g. AWS g4dn.xlarge / NVIDIA T4) with a 32K-token context window at full-precision KV cache (64K and 128K with quantized KV).

An Apple Silicon build of the same allocation is at baa-ai/Qwen3.8-27B-RAM-13GB-MLX (13.0 GB, vision tower retained).

Built for the case where the retrieved documents are the source of truth and the model's job is to interpret them — not to answer from its own memory. It was selected and validated to keep that behaviour intact under aggressive compression.

v2 (2026-09-27). This release replaces the v1 IQ3_M build with a RAM per-tensor mixed-precision allocation at the same 12.6 GB: per-tensor GGUF types (Q2_K to Q8_0) with importance-matrix calibration. WikiText-2 perplexity drops from 6.34 to 6.02 (−5.0%, better on 37 of 40 paired text chunks) with no change in size, and the build passes the full five-certificate bundle below. The v1 file remains available in the repository history.

⚠️ Requires a recent llama.cpp (build b10360 / Aug 2026 or newer). Qwen3.8 is a hybrid Gated Delta Net (linear-attention) + full-attention architecture (arch: qwen35). Stable Ollama and LM Studio releases may lag; use an up-to-date llama.cpp until downstream runtimes catch up.

Files

File	Quant	Size
`Qwen3.8-27B-RAM-13GB.gguf`	RAM mixed (Q2_K–Q8_0) + imatrix	12.58 GB

Metrics

Metric	Value
Size	12.6 GB (12,580,855,040 bytes)
Average bits per weight	3.74
Format	llama.cpp (GGUF), arch `qwen35`
WikiText-2 perplexity (40 × 2048 tokens)	6.02 (v1 IQ3_M at the same size: 6.34)
Deference to retrieved evidence	1.00
Reading accuracy from context	1.00
Long-context retrieval, needle at 3 depths + two-hop (8K / 32K)	48/48 / 32/32
GSM8K (50 questions, 768-token budget)	0.96
MMLU-math, forced answer (60 questions)	0.967
Agent-safety coherence gate (Fidelity Is Not Safety)	PASS (coherent fraction 0.0043)

Validated to lose nothing on faithfulness or reading versus the full-precision model: when a retrieved passage contradicts the model's own prior, it follows the passage 100% of the time, and reads the correct answer from context 100% of the time (30-item benches each). Retrieval of a planted fact at three depths and two-hop chaining across a 30K-token document were perfect in every trial.

Context window on a 16 GB GPU

Measured with llama-server on an NVIDIA Quadro P5000 (16,384 MiB, Pascal) with all layers offloaded (-ngl 99 -fa on). VRAM is nvidia-smi memory.used after a 2K-token warm-up, measured with the v1 file of identical size; throughput at 8K, 32K and 64K is the median over the long-context retrieval runs at that length, and at 128K the 2K-token warm-up. The KV cache of this architecture is small (16 of 64 layers use full attention), so long contexts fit:

Context	KV cache type	VRAM used	Prefill	Decode
8K	f16	12,425 MiB	160 tok/s	9.3 tok/s
32K	f16	13,985 MiB	130 tok/s	10.0 tok/s
64K	q8_0	14,359 MiB	104 tok/s	7.1 tok/s
128K	q4_0	14,807 MiB	80 tok/s	6.8 tok/s

128K at f16 or q8_0 KV does not fit. Retrieval quality (needle + two-hop) stayed perfect at 32K with f16 or q4_0 KV and at 64K with q8_0 KV.

Usage

brew install llama.cpp huggingface-cli

hf download baa-ai/Qwen3.8-27B-RAM-13GB-GGUF --include "*.gguf" --local-dir ./qwen3.8-27b-ram-13gb

llama-cli -m ./qwen3.8-27b-ram-13gb/Qwen3.8-27B-RAM-13GB.gguf -p "Hello!" -n 256 -ngl 99

Or via llama-server for an OpenAI-compatible HTTP API (drop-in for a retrieval-augmented reader), with the 32K context that fits a 16 GB card at full-precision KV:

llama-server -m ./qwen3.8-27b-ram-13gb/Qwen3.8-27B-RAM-13GB.gguf --port 8080 -ngl 99 --ctx-size 32768 -fa on

For 64K add -ctk q8_0 -ctv q8_0; for 128K, -ctk q4_0 -ctv q4_0. Also works with llama-cpp-python; Ollama and LM Studio need a build that supports qwen35.

Version history

Version	Date	Build	WikiText-2 PPL	Size
v2 (current)	2026-09-27	RAM per-tensor mixed precision + imatrix	6.02	12.58 GB
v1	2026-08-23	llama.cpp IQ3_M	6.34	12.58 GB

Compressed and capability-validated by baa.ai

Black Sheep AI Products

Black Sheep AI builds private AI with the Bounded AI Architecture (BAA): three layers, each bound to something you control, on infrastructure you control. Nothing leaves your boundary.

Ram (Reasoning Layer) — Full-capability frontier models, shrunk to fit smaller GPUs with reasoning kept and certified. They rely strictly on your Data Modules for knowledge, so you swap the model as better ones ship.

Paddock (Knowledge Plane) — Binds your Data Modules directly to the reasoning layer: one per topic, period, person, permission or tenant. Permission, freeze, hand back or delete each one on its own.

Watchman (GRC Layer) — Governance, risk and compliance in a single, complete audit log: every module permission, every bind, every model's provenance. Five certificates before anything goes live.

Shepherd — Takes a frontier model, compresses it into a Ram reasoning model, certifies it with Watchman, binds it to your Paddock, and deploys the Bounded AI Architecture to your infrastructure: your cloud, a Mac Studio, or an air-gapped facility.

Learn more at baa.ai — Private AI for enterprises whose data cannot leave the building.

Downloads last month: 417

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for baa-ai/Qwen3.8-27B-RAM-13GB-GGUF

Base model

Qwen/Qwen3.8-27B

Quantized

(1,757)

this model