One block, run again.
Nova Loop is built on SenseNova-Loop-9B, an open-weight model that gets deeper computation from the same weights by running its middle layers twice. This page covers the model, the engine that serves it, and the API.
Engine status
| Engine | SenseNova-Loop-9B |
|---|---|
| Status | checking… |
| Without the engine | Runs still do the Prelude and every read, and return the raw readings. |
| Thinking mode | Off by default for speed; the loop passes do the re-checking. |
SenseNova-Loop-9B at a glance
| Parameters | About 9B stored, about 14.6B worth of compute per token |
|---|---|
| Layers | 32 distinct, 56 runs per forward pass |
| Looped block | Layers 4 to 27, two passes, shared weights |
| Attention | Three linear-attention layers then one full-attention layer, repeating |
| Residual streams | 2, mixed by learned maps (mHC, Sinkhorn-normalised) |
| Context | 512K tokens; text and images in, text out |
| Licence | Apache 2.0, released 17 November 2026 |
How the loop maps to a Nova Loop run
Inside the model, a token passes layers 0 to 3 once, then the block of layers 4 to 27 twice (the second pass reads the first pass's output), then layers 28 to 31 and the output head once. Written short: head(C(B(B(A(h))))).
A Nova Loop run follows the same order one level up. The Prelude reads what the question names. The loop block is one prompt, applied again to its own draft together with a fresh read of every moving number. The Coda writes the answer, the chart and the receipt. SenseNova's own loop-scaling tests found three or four loops scored best on data analysis and coding; Nova Loop lets you pick one to four passes, or Auto.
Hosting the engine
The engine is any server that hosts the SenseNova-Loop weights behind an OpenAI-compatible /v1/chat/completions endpoint. Two ways the model's authors document:
# GGUF (Q4_K_M, about 5.8 GB) with the OpenSenseNova llama.cpp fork llama serve -hf sensenova/SenseNova-Loop-9B-GGUF:Q4_K_M -ngl 99 -c 16384 --port 8000 # vLLM with the SenseNova Loop support from vLLM PR #64832 vllm serve /path/to/SenseNova-Loop-9B --served-model-name sensenova-loop-9b --dtype bfloat16
At 4-bit weights with an 8-bit KV cache, a 64K context needs about 10 GiB of GPU memory.
Loop API
GET /api/loop says whether the engine is on. POST /api/loop runs a question and streams one JSON event per line (NDJSON) as each step lands.
curl -N https://novaloop.pw/api/loop \
-H 'content-type: application/json' \
-d '{"question": "How is $NVDA doing today?", "depth": "auto"}'
| start | engine name and whether it is on, depth, start time (UTC) |
|---|---|
| plan | the reads the Prelude picked, and whether rules or the model picked them |
| read | one per read: tool, argument, data or error, time taken |
| pass-start / pass | one per loop pass: answer, checks, what changed, confidence, time |
| need | extra reads a pass asked for |
| offline | the engine is off: the run stops after the reads |
| coda | final answer, chart data, sources, run hash |
| saved | the run is stored; GET /api/run?h=<hash> returns it |
Limits: 12 runs an hour per connection, questions up to 500 characters, depth "auto" or 1 to 4.