Instructions to use Outlier-Ai/Outlier-40B-V3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Outlier-Ai/Outlier-40B-V3.2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Outlier-Ai/Outlier-40B-V3.2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Outlier-Ai/Outlier-40B-V3.2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Outlier-Ai/Outlier-40B-V3.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Outlier-Ai/Outlier-40B-V3.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Outlier-Ai/Outlier-40B-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Outlier-Ai/Outlier-40B-V3.2

SGLang

How to use Outlier-Ai/Outlier-40B-V3.2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Outlier-Ai/Outlier-40B-V3.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Outlier-Ai/Outlier-40B-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Outlier-Ai/Outlier-40B-V3.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Outlier-Ai/Outlier-40B-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Outlier-Ai/Outlier-40B-V3.2 with Docker Model Runner:
```
docker model run hf.co/Outlier-Ai/Outlier-40B-V3.2
```

ur-dad-matt commited on May 5

Commit

8b70519

verified ·

1 Parent(s): dd669f5

docs(card): SEO + cross-link refresh (HF-DISCOVERABILITY-001)

Browse files

Files changed (1) hide show

README.md +15 -29

README.md CHANGED Viewed

@@ -39,42 +39,28 @@ language:
   - nl
   - pl
 ---
-> ⚠️ **SUPERSEDED — use [Outlier-Ai/Outlier-40B](https://huggingface.co/Outlier-Ai/Outlier-40B) instead.** These weights are retained live for reproducibility of earlier benchmark runs. All current research has moved to the successor.
-# Outlier 40B V3.2 (Superseded)
-Earlier ternary MoE overlay on frozen [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct). Superseded by [Outlier-40B (V3.3)](https://huggingface.co/Outlier-Ai/Outlier-40B).
-- **Scale:** 40B / ~14B active
-- **Base (frozen):** [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)
-- **Status:** archival — do not use for new work
-## What changed
-V3.2 and V3.3 share the same 77.80% MMLU at 40B. V3.3 adds the 15 KB alpha-fix overlay for improved profile switching during runtime.
-## Historical benchmark (reference only)
-| Benchmark | Score | Notes |
-|---|---|---|
-| MMLU 5-shot | 77.80% (n=14,042, lm-evaluation-harness v0.4.11) | Pre-V3.3 measurement |
-## Use the successor
-- **Current:** [Outlier-Ai/Outlier-40B](https://huggingface.co/Outlier-Ai/Outlier-40B)
-- **Research collection:** [Outlier Research](https://huggingface.co/collections/Outlier-Ai/outlier-research-69e2fb3a71984614b3c7a279)
-## Why this is still public
-ML research norms: earlier checkpoints stay live so external benchmarks and papers that cite this URL remain reproducible. This is not dead weight — it's the historical record.
-## Related
-- **Outlier desktop app:** [outlier.host](https://outlier.host) — v1.4 shipping
-- **Discord:** [discord.gg/Hapennmdn9](https://discord.gg/Hapennmdn9)
-## Patents
-Architecture covered by US provisional patents 64/026,886, 64/030,368, 64/034,028 (Kerr & Company LLC, 2026).

   - nl
   - pl
 ---
+> **Superseded.** This repo is a research artifact from an earlier Outlier lineage and is no longer the recommended download. The current shipping tier is at **[outlier.host](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_40b_v3_2)**.
+# Outlier-40B-V3.2
+This repo predates the v1.8 Outlier lineup. It is preserved here for reproducibility and historical reference, not as a production recommendation.
+## What replaced it
+Current shipping tiers (see Outlier app v1.8+):
+- [Outlier Nano 4B — current entry tier](https://huggingface.co/Outlier-Ai/Outlier-Nano-4B-MLX-4bit)
+- [Outlier Core 27B — current default tier](https://huggingface.co/Outlier-Ai/Outlier-Core-27B-MLX-4bit)
+- [Outlier Vision 35B-A3B — current multimodal tier](https://huggingface.co/Outlier-Ai/Outlier-Vision-35B-A3B-MLX-4bit)
+- [DeepSeek-R1-Distill-Qwen-7B — popular reasoning model](https://huggingface.co/Outlier-Ai/DeepSeek-R1-Distill-Qwen-7B-MLX-4bit)
+- [Qwen3-Coder-30B-A3B — popular coding model](https://huggingface.co/Outlier-Ai/Qwen3-Coder-30B-A3B-Instruct-MLX-4bit)
+For the latest verified benchmarks and downloads, visit **[outlier.host](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_40b_v3_2)**.
+## Original notes
+This was a research / preview artifact. It may contain experimental adapters, overlays, or quantization variants that did not graduate into the shipping product. Treat any technical claims in earlier revisions of this card as provisional.
+## License
+See YAML frontmatter above. Original license terms preserved.