Instructions to use divagr1925/QwenPU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use divagr1925/QwenPU with Transformers:

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

pipe = pipeline("text-generation", model="divagr1925/QwenPU")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("divagr1925/QwenPU")
model = AutoModelForCausalLM.from_pretrained("divagr1925/QwenPU", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use divagr1925/QwenPU with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "divagr1925/QwenPU"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "divagr1925/QwenPU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/divagr1925/QwenPU

SGLang

How to use divagr1925/QwenPU 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 "divagr1925/QwenPU" \
    --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": "divagr1925/QwenPU",
		"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 "divagr1925/QwenPU" \
        --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": "divagr1925/QwenPU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use divagr1925/QwenPU with Docker Model Runner:
```
docker model run hf.co/divagr1925/QwenPU
```

Code on GitHub · Qwenputer · Base model: Qwen/Qwen3.5-4B · Apache-2.0

QwenPU is Qwen3.5-4B with a 32-bit RISC-V CPU and a vector unit compiled into its weights. The vector unit runs a whole neural network inside the model's forward passes: Andrej Karpathy's stories260K, the 260K-parameter Llama from llama2.c, runs as a program on it and writes its stories.

It's part of Qwenputer: the same CPU, compiled into transformer layers in front of Qwen's own, every weight set by a compiler, with Qwen3.5's Gated DeltaNet state as its memory. Qwenputer-npu gave that CPU dot-product instructions. QwenPU gives it a vector unit of its own: separate memories in DeltaNet heads, 64-lane matrix rows a token, and whole vector results streamed through the token stream.

Work in progress. QwenPU is exact, but not yet small: the checkpoint is 26.7 GB, so it needs a 40 GB or larger GPU to load whole. The story demo and the checks run the computer's layers on their own and fit a 24 GB GPU. Trimming the hidden size, and with it the checkpoint, is next.

A language model inside the language model

stories260K is a C program here (guests/stories260k/stories_vx.c). Its int4 weights sit in the vector unit's weight memory, loaded from the program, and every matrix row, residual add, softmax and attention read is a vector op. None of it is compiled into the checkpoint, so any model that fits runs the same way.

Build of stories260K	Trace tokens per story token
Plain C, int8 weights	2,430,000
Qwenputer-npu: VDOT + SMAQA	225,000
QwenPU: the vector unit	53,000

QwenPU writing a story: stories260K runs on the vector unit inside Qwen3.5.

Every build writes the same story, token for token:

Once upon a time, there was a little girl named Lily. She loved to play outside in the park. One day, she saw a big, red ball. She wanted to play with it, but it was too high

The vector unit

Op	Does
`VMAT`	int8 · int4 matrix rows, 64 lanes a token, times the row scale; or the argmax
`VQ`	quantizes a vector register into int8 activations or a K / V cache row
`VEW`	residual add, SiLU-gated product, RoPE
`VMATR`	attention scores over the K cache; probabilities times the V cache
`VEXP`	exp-table softmax numerators
`VRED`	sum or sum of squares of the activations
`VGET`, `VPUT`	move values between the CPU and the unit

Its memories are DeltaNet heads: 16 vector registers of 64 words, 384 int8 activations, 4,152 row-chunks of int4 weights, and K / V caches for 32 positions. An op's record starts with config tokens carrying its operands, then streams its results, and each token is one exact step of the compiled layers. SiLU and exp are fixed-point function units, generic like the CPU's adders.

Checks

Every vector op runs random test programs on this checkpoint's own chip layers, teacher-forced against a reference model of the unit, along with the first 30,000 steps of the story program: zero mismatches.
The circuit's executor writes the whole story free-running on a GPU, checked against the reference at every one of its 3,184,920 steps: exact. It runs at about 3,300 trace tokens a second on an L4, so a story token takes about 16 seconds, against 41 for Qwenputer-npu.

Quickstart

git clone https://github.com/divagr18/QwenPU && cd QwenPU && uv sync --extra hf
uv run python guests/stories260k/storyrun.py guests/stories260k/stories_vx.elf --vx
hf download divagr1925/QwenPU --local-dir qwenpu
uv run python -m chipformer.rv.vxcheck qwenpu guests/stories260k/stories_vx.elf

storyrun writes the story on the computer's executor; vxcheck runs the vector unit on this checkpoint's layers (--chip-only loads only those on the GPU, about 13 GB).

Model details


Base	Qwen/Qwen3.5-4B, Qwen's own weights unchanged
Architecture	stock `Qwen3_5ForCausalLM` (text only); config-only changes
Computer	13 compiled layers before Qwen's 32: RV32IM + Zba + bignum unit + the vector unit
Hidden size	5120 (Qwen's 2560 plus the computer's dims)
Vocabulary	Qwen's, plus 394,164 trace tokens
Size	26.7 GB in bf16, mostly zero padding
Precision	exact in bf16

Citation

@software{agrawal2026qwenputer,
  author  = {Agrawal, Divyansh},
  title   = {{Qwenputer}: a computer compiled into the weights of a language model},
  year    = {2026},
  url     = {https://github.com/divagr18/qwenputer},
  license = {MIT}
}

License

Apache-2.0. This is a modified version of Qwen/Qwen3.5-4B: the config is widened and computer layers are added, but Qwen's own weights are unchanged. stories260K and llama2.c are by Andrej Karpathy (MIT).

Downloads last month: 677

Safetensors

Model size

13B params

Tensor type

BF16

F32

Model tree for divagr1925/QwenPU

Qwen/Qwen3.5-4B

Merge model

this model

Collection including divagr1925/QwenPU

Qwenputer

Collection

Qwen3.5-4B with a real RISC-V CPU and filesystem built into its DeltaNet layers. Exact, no tools, no Python, loads with transformers. • 4 items • Updated about 15 hours ago • 2