169Pi

Alpie_seed

README

License: apache-2.0

Alpie Seed Highlights

Unified vision-language model: text, image, and video input on the Qwen3.5-9B architecture.
Reasoning and coding: post-trained with supervised fine-tuning and GRPO; supports thinking and non-thinking modes.
262K native context for long documents and extended conversations.
Flexible deployment: FP16 weights plus 2-bit, 3-bit, and 4-bit GGUF builds.
Open license: Apache 2.0.

Available On

Table with columns: Platform, Link
Platform	Link
Hugging Face (GGUF)	169Pi/Alpie_Seed_GGUF
Ollama	ollama.com/169pi/alpie-seed
Kaggle	kaggle.com/models/alpie/alpie-seed-9b

Ollama

Run Alpie Seed directly from the Ollama library:

bash

ollama run 169pi/alpie-seed

Available tags:

Table with columns: Name, Size, Context, Input
Name	Size	Context	Input
`alpie-seed:latest`	5.6 GB	256K	Text
`alpie-seed:q2`	3.8 GB	256K	Text
`alpie-seed:q3`	4.6 GB	256K	Text
`alpie-seed:vision`	6.6 GB	256K	Text, Image

To run a specific tag:

bash

ollama run 169pi/alpie-seed:q2ollama run 169pi/alpie-seed:vision

Model Overview

Type: Causal Language Model with Vision Encoder
Training Stage: Post-training (SFT + GRPO) on Qwen3.5-9B
Language Model
- Number of Parameters: 9B
- Hidden Dimension: 4096
- Token Embedding: 248320 (Padded)
- Number of Layers: 32
- Hidden Layout: 8 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
- Gated DeltaNet:
  - Number of Linear Attention Heads: 32 for V and 16 for QK
  - Head Dimension: 128
- Gated Attention:
  - Number of Attention Heads: 16 for Q and 4 for KV
  - Head Dimension: 256
  - Rotary Position Embedding Dimension: 64
- Feed Forward Network:
  - Intermediate Dimension: 12288
- LM Output: 248320 (Padded)
- MTP: trained with multi-steps
Vision Encoder: 27-layer Vision Transformer
Context Length: 262,144 tokens

The architecture is retained from Qwen3.5-9B; Alpie Seed's adaptation is carried out through post-training rather than a structural redesign.

Training

Alpie Seed uses a two-stage post-training pipeline.

Supervised fine-tuning (SFT): a DORA adapter is trained to improve instruction following, response quality, and task performance.
Group Relative Policy Optimization (GRPO): a trainable DoRA adapter is optimized while the SFT adapter is kept as a frozen reference policy. The GRPO stage uses a 4-bit NF4 base with double quantization and BF16 computation, and the trained adapter is merged into the base model at its original precision for release.

Benchmark Results

Evaluation Settings Note: All benchmarks were evaluated with extended thinking enabled (enable_thinking: true), a maximum generation length of max_tokens: 65536, and temperature: 0.0.

Alpie Seed scores are from the FP16 model and do not apply to the 2-bit, 3-bit, or 4-bit variants. Bold indicates the best score in each row. Comparison-model scores are taken from published model cards and reports (including the Qwen3.5-9B model card).

Language

Vision Language

SWE-Bench Verified: resolved rate using Mini-SWE-agent, with retries disabled.
Comparison-model scores were not re-run by 169Pi, and harnesses, prompts, and benchmark versions differ, so cross-model comparisons are indicative rather than strictly like-for-like. Scores vary with dataset versions, prompts, evaluation harnesses, and inference settings.
Empty cells (--) indicate scores not yet available or not applicable.
Sources: Ministral 3 8B model card, NVIDIA Nemotron 3.5 Lightning evaluation, Qwen3.5-9B model card, Gemma 4 model card, GPT-OSS evaluation, and Sarvam-30B model card.

Quickstart

Install dependencies

Alpie Seed support requires a recent Transformers release (Transformers 5 or later).

bash

pip install -U "transformers>=5.2.0" torch torchvision pillow accelerate

Serve with vLLM (OpenAI-compatible API)

Start the standard Alpie Seed 9B server:

bash

vllm serve 169Pi/Alpie_seed \  --port 8000 \  --max-model-len 262144 \  --reasoning-parser qwen3

To enable automatic tool-call parsing, use this command instead:

bash

vllm serve 169Pi/Alpie_seed \  --port 8000 \  --max-model-len 262144 \  --reasoning-parser qwen3 \  --enable-auto-tool-choice \  --tool-call-parser qwen3_coder

The API is available at http://localhost:8000/v1. The tool-calling options enable vLLM to parse model-generated tool calls; your application is still responsible for executing the requested tools and returning their results.

Run with Transformers

The following examples load the full vision-language checkpoint using AutoModelForImageTextToText and AutoProcessor. They retain the model's multimodal architecture. The enable_thinking argument is passed to the chat template to select the response mode.

1. Thinking mode (`enable_thinking=True`)

python

import torchfrom transformers import AutoModelForImageTextToText, AutoProcessor MODEL_ID = "169Pi/Alpie_seed" processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForImageTextToText.from_pretrained(    MODEL_ID,    torch_dtype="auto",    device_map="auto",)model.eval() messages = [    {        "role": "user",        "content": [            {"type": "text", "text": "Explain why the sky appears blue."}        ],    }] inputs = processor.apply_chat_template(    messages,    tokenize=True,    add_generation_prompt=True,    enable_thinking=True,    return_dict=True,    return_tensors="pt",).to(model.device) with torch.inference_mode():    output_ids = model.generate(        **inputs,        max_new_tokens=4096,        do_sample=True,        temperature=0.7,        top_p=0.8,    ) new_tokens = output_ids[0, inputs["input_ids"].shape[1]:]response = processor.decode(new_tokens, skip_special_tokens=True)print(response)

2. Non-thinking mode (`enable_thinking=False`)

python

import torchfrom transformers import AutoModelForImageTextToText, AutoProcessor MODEL_ID = "169Pi/Alpie_seed" processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForImageTextToText.from_pretrained(    MODEL_ID,    torch_dtype="auto",    device_map="auto",)model.eval() messages = [    {        "role": "user",        "content": [            {"type": "text", "text": "Explain why the sky appears blue in two sentences."}        ],    }] inputs = processor.apply_chat_template(    messages,    tokenize=True,    add_generation_prompt=True,    enable_thinking=False,    return_dict=True,    return_tensors="pt",).to(model.device) with torch.inference_mode():    output_ids = model.generate(        **inputs,        max_new_tokens=512,        do_sample=True,        temperature=0.7,        top_p=0.8,    ) new_tokens = output_ids[0, inputs["input_ids"].shape[1]:]response = processor.decode(new_tokens, skip_special_tokens=True)print(response)

3. Tool calling with Transformers

Transformers can format the available tool definitions into the prompt. The model generates a tool-call request; your application must parse the request, execute the corresponding function, append the tool result, and ask the model to continue. This example demonstrates generating and inspecting a tool call; it does not execute external tools automatically.

python

import jsonimport torchfrom transformers import AutoModelForImageTextToText, AutoProcessor MODEL_ID = "169Pi/Alpie_seed" processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForImageTextToText.from_pretrained(    MODEL_ID,    torch_dtype="auto",    device_map="auto",)model.eval() tools = [    {        "type": "function",        "function": {            "name": "get_weather",            "description": "Get the current weather for a city.",            "parameters": {                "type": "object",                "properties": {                    "city": {                        "type": "string",                        "description": "The city to check.",                    }                },                "required": ["city"],            },        },    }] messages = [    {        "role": "user",        "content": [            {"type": "text", "text": "What is the weather like in Patna?"}        ],    }] inputs = processor.apply_chat_template(    messages,    tools=tools,    tokenize=True,    add_generation_prompt=True,    enable_thinking=True,    return_dict=True,    return_tensors="pt",).to(model.device) with torch.inference_mode():    output_ids = model.generate(        **inputs,        max_new_tokens=1024,        do_sample=True,        temperature=0.7,        top_p=0.8,    ) new_tokens = output_ids[0, inputs["input_ids"].shape[1]:]generated_text = processor.decode(new_tokens, skip_special_tokens=False)print("Model output:")print(generated_text) # Tool execution is application-side. Inspect the generated tool-call# structure, validate its arguments, and dispatch only to tools you trust.

For image or video inputs, provide the corresponding image/video content items in the user message and use the same AutoProcessor + AutoModelForImageTextToText loading pattern. See the upstream Qwen3.5 documentation for multimodal message examples and framework-specific details.

Citation

If you use Alpie Seed 9B in your work, please cite:

bibtex

@misc{alpie_seed_9b_2026,  title        = {Alpie Seed 9B},  author       = {{169Pi AI}},  year         = {2026},  howpublished = {\url{https://huggingface.co/169Pi/Alpie_seed}}}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

169Pi

Model Tree

Base

Qwen/Qwen3.5-9B

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Alpie Seed Highlights

Unified vision-language model: text, image, and video input on the Qwen3.5-9B architecture.
Reasoning and coding: post-trained with supervised fine-tuning and GRPO; supports thinking and non-thinking modes.
262K native context for long documents and extended conversations.
Flexible deployment: FP16 weights plus 2-bit, 3-bit, and 4-bit GGUF builds.
Open license: Apache 2.0.

Available On

Table with columns: Platform, Link
Platform	Link
Hugging Face (GGUF)	169Pi/Alpie_Seed_GGUF
Ollama	ollama.com/169pi/alpie-seed
Kaggle	kaggle.com/models/alpie/alpie-seed-9b

Ollama

Run Alpie Seed directly from the Ollama library:

bash

ollama run 169pi/alpie-seed

Available tags:

Table with columns: Name, Size, Context, Input
Name	Size	Context	Input
`alpie-seed:latest`	5.6 GB	256K	Text
`alpie-seed:q2`	3.8 GB	256K	Text
`alpie-seed:q3`	4.6 GB	256K	Text
`alpie-seed:vision`	6.6 GB	256K	Text, Image

To run a specific tag:

bash

ollama run 169pi/alpie-seed:q2ollama run 169pi/alpie-seed:vision

ollama run 169pi/alpie-seed:q2ollama run 169pi/alpie-seed:vision

Model Overview

Type: Causal Language Model with Vision Encoder
Training Stage: Post-training (SFT + GRPO) on Qwen3.5-9B
Language Model
- Number of Parameters: 9B
- Hidden Dimension: 4096
- Token Embedding: 248320 (Padded)
- Number of Layers: 32
- Hidden Layout: 8 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
- Gated DeltaNet:
  - Number of Linear Attention Heads: 32 for V and 16 for QK
  - Head Dimension: 128
- Gated Attention:
  - Number of Attention Heads: 16 for Q and 4 for KV
  - Head Dimension: 256
  - Rotary Position Embedding Dimension: 64
- Feed Forward Network:
  - Intermediate Dimension: 12288
- LM Output: 248320 (Padded)
- MTP: trained with multi-steps
Vision Encoder: 27-layer Vision Transformer
Context Length: 262,144 tokens

The architecture is retained from Qwen3.5-9B; Alpie Seed's adaptation is carried out through post-training rather than a structural redesign.

Training

Alpie Seed uses a two-stage post-training pipeline.

Supervised fine-tuning (SFT): a DORA adapter is trained to improve instruction following, response quality, and task performance.
Group Relative Policy Optimization (GRPO): a trainable DoRA adapter is optimized while the SFT adapter is kept as a frozen reference policy. The GRPO stage uses a 4-bit NF4 base with double quantization and BF16 computation, and the trained adapter is merged into the base model at its original precision for release.

Benchmark Results

Evaluation Settings Note: All benchmarks were evaluated with extended thinking enabled (enable_thinking: true), a maximum generation length of max_tokens: 65536, and temperature: 0.0.

Alpie Seed scores are from the FP16 model and do not apply to the 2-bit, 3-bit, or 4-bit variants. Bold indicates the best score in each row. Comparison-model scores are taken from published model cards and reports (including the Qwen3.5-9B model card).

Language

Vision Language

SWE-Bench Verified: resolved rate using Mini-SWE-agent, with retries disabled.
Comparison-model scores were not re-run by 169Pi, and harnesses, prompts, and benchmark versions differ, so cross-model comparisons are indicative rather than strictly like-for-like. Scores vary with dataset versions, prompts, evaluation harnesses, and inference settings.
Empty cells (--) indicate scores not yet available or not applicable.
Sources: Ministral 3 8B model card, NVIDIA Nemotron 3.5 Lightning evaluation, Qwen3.5-9B model card, Gemma 4 model card, GPT-OSS evaluation, and Sarvam-30B model card.

Quickstart

Install dependencies

Alpie Seed support requires a recent Transformers release (Transformers 5 or later).

bash

pip install -U "transformers>=5.2.0" torch torchvision pillow accelerate

pip install -U "transformers>=5.2.0" torch torchvision pillow accelerate

Serve with vLLM (OpenAI-compatible API)

Start the standard Alpie Seed 9B server:

bash

vllm serve 169Pi/Alpie_seed \  --port 8000 \  --max-model-len 262144 \  --reasoning-parser qwen3

vllm serve 169Pi/Alpie_seed \  --port 8000 \  --max-model-len 262144 \  --reasoning-parser qwen3

To enable automatic tool-call parsing, use this command instead:

bash

vllm serve 169Pi/Alpie_seed \  --port 8000 \  --max-model-len 262144 \  --reasoning-parser qwen3 \  --enable-auto-tool-choice \  --tool-call-parser qwen3_coder

vllm serve 169Pi/Alpie_seed \  --port 8000 \  --max-model-len 262144 \  --reasoning-parser qwen3 \  --enable-auto-tool-choice \  --tool-call-parser qwen3_coder

Run with Transformers

1. Thinking mode (`enable_thinking=True`)

python

import torchfrom transformers import AutoModelForImageTextToText, AutoProcessor MODEL_ID = "169Pi/Alpie_seed" processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForImageTextToText.from_pretrained(    MODEL_ID,    torch_dtype="auto",    device_map="auto",)model.eval() messages = [    {        "role": "user",        "content": [            {"type": "text", "text": "Explain why the sky appears blue."}        ],    }] inputs = processor.apply_chat_template(    messages,    tokenize=True,    add_generation_prompt=True,    enable_thinking=True,    return_dict=True,    return_tensors="pt",).to(model.device) with torch.inference_mode():    output_ids = model.generate(        **inputs,        max_new_tokens=4096,        do_sample=True,        temperature=0.7,        top_p=0.8,    ) new_tokens = output_ids[0, inputs["input_ids"].shape[1]:]response = processor.decode(new_tokens, skip_special_tokens=True)print(response)

import torchfrom transformers import AutoModelForImageTextToText, AutoProcessor MODEL_ID = "169Pi/Alpie_seed" processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForImageTextToText.from_pretrained(    MODEL_ID,    torch_dtype="auto",    device_map="auto",)model.eval() messages = [    {        "role": "user",        "content": [            {"type": "text", "text": "Explain why the sky appears blue."}        ],    }] inputs = processor.apply_chat_template(    messages,    tokenize=True,    add_generation_prompt=True,    enable_thinking=True,    return_dict=True,    return_tensors="pt",).to(model.device) with torch.inference_mode():    output_ids = model.generate(        **inputs,        max_new_tokens=4096,        do_sample=True,        temperature=0.7,        top_p=0.8,    ) new_tokens = output_ids[0, inputs["input_ids"].shape[1]:]response = processor.decode(new_tokens, skip_special_tokens=True)print(response)

2. Non-thinking mode (`enable_thinking=False`)

python

import torchfrom transformers import AutoModelForImageTextToText, AutoProcessor MODEL_ID = "169Pi/Alpie_seed" processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForImageTextToText.from_pretrained(    MODEL_ID,    torch_dtype="auto",    device_map="auto",)model.eval() messages = [    {        "role": "user",        "content": [            {"type": "text", "text": "Explain why the sky appears blue in two sentences."}        ],    }] inputs = processor.apply_chat_template(    messages,    tokenize=True,    add_generation_prompt=True,    enable_thinking=False,    return_dict=True,    return_tensors="pt",).to(model.device) with torch.inference_mode():    output_ids = model.generate(        **inputs,        max_new_tokens=512,        do_sample=True,        temperature=0.7,        top_p=0.8,    ) new_tokens = output_ids[0, inputs["input_ids"].shape[1]:]response = processor.decode(new_tokens, skip_special_tokens=True)print(response)

import torchfrom transformers import AutoModelForImageTextToText, AutoProcessor MODEL_ID = "169Pi/Alpie_seed" processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForImageTextToText.from_pretrained(    MODEL_ID,    torch_dtype="auto",    device_map="auto",)model.eval() messages = [    {        "role": "user",        "content": [            {"type": "text", "text": "Explain why the sky appears blue in two sentences."}        ],    }] inputs = processor.apply_chat_template(    messages,    tokenize=True,    add_generation_prompt=True,    enable_thinking=False,    return_dict=True,    return_tensors="pt",).to(model.device) with torch.inference_mode():    output_ids = model.generate(        **inputs,        max_new_tokens=512,        do_sample=True,        temperature=0.7,        top_p=0.8,    ) new_tokens = output_ids[0, inputs["input_ids"].shape[1]:]response = processor.decode(new_tokens, skip_special_tokens=True)print(response)

3. Tool calling with Transformers

python

import jsonimport torchfrom transformers import AutoModelForImageTextToText, AutoProcessor MODEL_ID = "169Pi/Alpie_seed" processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForImageTextToText.from_pretrained(    MODEL_ID,    torch_dtype="auto",    device_map="auto",)model.eval() tools = [    {        "type": "function",        "function": {            "name": "get_weather",            "description": "Get the current weather for a city.",            "parameters": {                "type": "object",                "properties": {                    "city": {                        "type": "string",                        "description": "The city to check.",                    }                },                "required": ["city"],            },        },    }] messages = [    {        "role": "user",        "content": [            {"type": "text", "text": "What is the weather like in Patna?"}        ],    }] inputs = processor.apply_chat_template(    messages,    tools=tools,    tokenize=True,    add_generation_prompt=True,    enable_thinking=True,    return_dict=True,    return_tensors="pt",).to(model.device) with torch.inference_mode():    output_ids = model.generate(        **inputs,        max_new_tokens=1024,        do_sample=True,        temperature=0.7,        top_p=0.8,    ) new_tokens = output_ids[0, inputs["input_ids"].shape[1]:]generated_text = processor.decode(new_tokens, skip_special_tokens=False)print("Model output:")print(generated_text) # Tool execution is application-side. Inspect the generated tool-call# structure, validate its arguments, and dispatch only to tools you trust.

import jsonimport torchfrom transformers import AutoModelForImageTextToText, AutoProcessor MODEL_ID = "169Pi/Alpie_seed" processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForImageTextToText.from_pretrained(    MODEL_ID,    torch_dtype="auto",    device_map="auto",)model.eval() tools = [    {        "type": "function",        "function": {            "name": "get_weather",            "description": "Get the current weather for a city.",            "parameters": {                "type": "object",                "properties": {                    "city": {                        "type": "string",                        "description": "The city to check.",                    }                },                "required": ["city"],            },        },    }] messages = [    {        "role": "user",        "content": [            {"type": "text", "text": "What is the weather like in Patna?"}        ],    }] inputs = processor.apply_chat_template(    messages,    tools=tools,    tokenize=True,    add_generation_prompt=True,    enable_thinking=True,    return_dict=True,    return_tensors="pt",).to(model.device) with torch.inference_mode():    output_ids = model.generate(        **inputs,        max_new_tokens=1024,        do_sample=True,        temperature=0.7,        top_p=0.8,    ) new_tokens = output_ids[0, inputs["input_ids"].shape[1]:]generated_text = processor.decode(new_tokens, skip_special_tokens=False)print("Model output:")print(generated_text) # Tool execution is application-side. Inspect the generated tool-call# structure, validate its arguments, and dispatch only to tools you trust.

Citation

If you use Alpie Seed 9B in your work, please cite:

bibtex

@misc{alpie_seed_9b_2026,  title        = {Alpie Seed 9B},  author       = {{169Pi AI}},  year         = {2026},  howpublished = {\url{https://huggingface.co/169Pi/Alpie_seed}}}

@misc{alpie_seed_9b_2026,  title        = {Alpie Seed 9B},  author       = {{169Pi AI}},  year         = {2026},  howpublished = {\url{https://huggingface.co/169Pi/Alpie_seed}}}

Alpie_seed

README

Alpie Seed Highlights

Available On

Ollama

Model Overview

Training

Benchmark Results

Language

Vision Language

Quickstart

Install dependencies

Serve with vLLM (OpenAI-compatible API)

Run with Transformers

1. Thinking mode (enable_thinking=True)

2. Non-thinking mode (enable_thinking=False)

3. Tool calling with Transformers

Citation

Explore FriendliAI today

README

Alpie Seed Highlights

Available On

Ollama

Model Overview

Training

Benchmark Results

Language

Vision Language

Quickstart

Install dependencies

Serve with vLLM (OpenAI-compatible API)

Run with Transformers

1. Thinking mode (enable_thinking=True)

2. Non-thinking mode (enable_thinking=False)

3. Tool calling with Transformers

Citation

1. Thinking mode (`enable_thinking=True`)

2. Non-thinking mode (`enable_thinking=False`)

1. Thinking mode (`enable_thinking=True`)

2. Non-thinking mode (`enable_thinking=False`)