Text Generation
MLX
Safetensors
qwen2
4-bit precision
4bit
apple-silicon
chain-of-thought
chat
conversational
deepseek
deepseek-r1
deepseek-r1-distill
edge-ai
function-calling
instruct
local-llm
m1
m2
m3
m4
mac
mac-mini
mac-studio
macbook-air
macbook-pro
macos
metal
mlx-community
mlx-lm
no-cloud
offline
on-device
outlier
outlier-app
private
quantized
r1
r1-distill
reasoning
thinking
Instructions to use Outlier-Ai/DeepSeek-R1-Distill-Qwen-32B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Outlier-Ai/DeepSeek-R1-Distill-Qwen-32B-MLX-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("Outlier-Ai/DeepSeek-R1-Distill-Qwen-32B-MLX-4bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use Outlier-Ai/DeepSeek-R1-Distill-Qwen-32B-MLX-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "Outlier-Ai/DeepSeek-R1-Distill-Qwen-32B-MLX-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "Outlier-Ai/DeepSeek-R1-Distill-Qwen-32B-MLX-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Outlier-Ai/DeepSeek-R1-Distill-Qwen-32B-MLX-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
Fix Rule 142 + add collection links
Browse files
README.md
CHANGED
|
@@ -85,7 +85,7 @@ picker under `reasoning`.
|
|
| 85 |
This is a canonically-named twin of [Outlier-Ai/Outlier-R1-Distill-32B-MLX-4bit](https://huggingface.co/Outlier-Ai/Outlier-R1-Distill-32B-MLX-4bit).
|
| 86 |
Same weights, same quant, different name. The branded repo carries the Outlier
|
| 87 |
identity; this one carries the upstream identity so it's findable via searches
|
| 88 |
-
like "deepseek-r1-distill-qwen-32b 4bit mlx". Use whichever path you
|
| 89 |
point to the same files.
|
| 90 |
|
| 91 |
## Provenance
|
|
@@ -103,6 +103,12 @@ point to the same files.
|
|
| 103 |
- **Founders lifetime ($200, 500-seat cap):** [buy.polar.sh](https://buy.polar.sh/polar_cl_mJfYZsEpEMDcYrgxzvTdnahSeSQNq1UYLqV0l08CUhW)
|
| 104 |
- **Discord:** [discord.gg/Hapennmdn9](https://discord.gg/Hapennmdn9)
|
| 105 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
## Attribution
|
| 107 |
|
| 108 |
Base model by the upstream author (see [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)). Outlier contributes
|
|
|
|
| 85 |
This is a canonically-named twin of [Outlier-Ai/Outlier-R1-Distill-32B-MLX-4bit](https://huggingface.co/Outlier-Ai/Outlier-R1-Distill-32B-MLX-4bit).
|
| 86 |
Same weights, same quant, different name. The branded repo carries the Outlier
|
| 87 |
identity; this one carries the upstream identity so it's findable via searches
|
| 88 |
+
like "deepseek-r1-distill-qwen-32b 4bit mlx". Use whichever path you came across — both
|
| 89 |
point to the same files.
|
| 90 |
|
| 91 |
## Provenance
|
|
|
|
| 103 |
- **Founders lifetime ($200, 500-seat cap):** [buy.polar.sh](https://buy.polar.sh/polar_cl_mJfYZsEpEMDcYrgxzvTdnahSeSQNq1UYLqV0l08CUhW)
|
| 104 |
- **Discord:** [discord.gg/Hapennmdn9](https://discord.gg/Hapennmdn9)
|
| 105 |
|
| 106 |
+
## Collections
|
| 107 |
+
|
| 108 |
+
- **Outlier for Apple Silicon (MLX):** [huggingface.co/collections/Outlier-Ai/outlier-consumer-edition-69e2fb4a0df119ea1747275e](https://huggingface.co/collections/Outlier-Ai/outlier-consumer-edition-69e2fb4a0df119ea1747275e)
|
| 109 |
+
- **Outlier Research MoE:** [huggingface.co/collections/Outlier-Ai/outlier-research-69e2fb3a71984614b3c7a279](https://huggingface.co/collections/Outlier-Ai/outlier-research-69e2fb3a71984614b3c7a279)
|
| 110 |
+
- **Outlier Server V3.2:** [huggingface.co/collections/Outlier-Ai/outlier-server-v32-69e2fb4b71984614b3c7a4a3](https://huggingface.co/collections/Outlier-Ai/outlier-server-v32-69e2fb4b71984614b3c7a4a3)
|
| 111 |
+
|
| 112 |
## Attribution
|
| 113 |
|
| 114 |
Base model by the upstream author (see [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)). Outlier contributes
|