Sign in

Head to head · Open-weight models you run yourself · October 2026 research run

Kronos vs SenseNova-Loop-9B-Preview

Kronos scores 55.2 (C) on agent readiness against SenseNova-Loop-9B-Preview's 46.8 (D), and leads in 2 of 4 scored categories. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons

KronosYu Shi (shiyu-coder, NeoQuasar), Tsinghua University · Open-weight model C55.2/100#122 of 160 open-weight models SenseNova-Loop-9B-PreviewSenseTime (SenseNova) · Open-weight model D46.8/100#155 of 160 open-weight models

Which one, for what

Kronos C

Best for Agents that need a quick local forecast or synthetic sample of a candlestick series on modest hardware, for research or as one input among others.

Ahead on

  • Reach, 55 against 40
  • Documentation and upkeep, 61 against 44

Watch for

Runs only through the publisher's own PyTorch code from GitHub, in no named runtime and with no quantised build

SenseNova-Loop-9B-Preview D

Best for Researchers who want to study or fine-tune a looped transformer, more than agents that need a model to call today

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No released runtime runs it. vLLM and SGLang need unmerged pull requests

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Documentation and upkeep Kronos +17

Kronos 61

Model card 11, intended use, architecture, parameters and context are there, limitations, languages and a cut-off aren't. Training data 20, the paper lists every exchange with asset and observation counts, the filtering and a June 2024 end. Last change 5, the reference code on 13 April 2026 (still the newest commit on 4 November, 205 days) and the Hub repositories on 9 September 2025. Responsiveness 20, the publisher answered 10 of 18 Hugging Face discussions (recounted by script on 4 November), though none since 24 November 2025, and the seven opened since April 2026 have no reply from it. Version policy 5, a first release. File health 0, the cards point to example data the repository has deleted and to licence and requirements links on a branch that doesn't exist.

SenseNova-Loop-9B-Preview 44

Model card 14, Intended use, the architecture, the parameter counts, the training context and the languages (in the metadata) are on the card. Training data 5, one general sentence on the recipes, with no sources, sizes or cut-off. Last change 20, the last commit, on 2 November 2026, reworked the speculative decoding section of the card, 8 days before this check. Responsiveness 0, none of the 5 discussions that aren't pull requests (30 October to 9 November 2026) has a reply from a sensenova member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, A first release, labelled a preview, with dated news on the card. File health 0, the files contradict the card on precision. 14 + 5 + 20 + 0 + 5 + 0 = 44.

Reach Kronos +15

Kronos 55

Memory 30, the publisher's Kronos-mini with its tokeniser is 0.03 GB and even Kronos-base is 0.43 GB in FP32. Runtimes 0, it runs only through the publisher's own PyTorch package from GitHub, and none of the six named runtimes supports it. Builds 0, FP32 safetensors only. Terms 15, MIT with nothing added. Download 10, nothing is gated. Hosted 0, no inference provider or publisher API serves it (provider mapping still empty on 4 November).

SenseNova-Loop-9B-Preview 40

Memory 15, the only build is the safetensors set, 38.14 GB with its MTP head, since the Hub counts 9.41B of its parameters in F32. Runtimes 0, none of the six runs it in a released version. Builds 0, SenseNova publishes one set of weights and no quantised build. Terms 15, Apache 2.0 in the card's metadata and on the card, which links the LICENSE in the GitHub repository, and nothing added. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it, and the card names no API that serves it. 15 + 0 + 0 + 15 + 10 + 0 = 40.

Score by category

CategoryWeight this runKronosSenseNova-Loop-9B-PreviewEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255540Kronos +15
Risk20%205050even
Agent interface10%106060even
Documentation and upkeep10%106144Kronos +17
Negative events≤1500
TotalC 55.2/100D 46.8/100

Facts side by side

FactKronosSenseNova-Loop-9B-Preview
KindOpen-weight modelOpen-weight model
VendorYu Shi (shiyu-coder, NeoQuasar), Tsinghua UniversitySenseTime (SenseNova)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceMITApache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-04-132026-11-02
Terms last updatedno document linkednot read yet
Privacy policy last updatedno document linkedno document linked
Popularity43k starsnone

Verdicts

Kronos

Forecasts the next price bars from a history of up to 512 candlestick bars. Every size fits in under 0.5 GB and runs on a CPU, but only through the publisher's own Python package. Nobody has benchmarked it independently, its quickstart data was deleted from the repository, and the publisher hasn't replied since November 2025.

SenseNova-Loop-9B-Preview

An unusual architecture under Apache 2.0, with a 256K training context, a thinking switch and tool calling in the template. It's a preview in practice too: no released runtime runs it, loading it runs the repository's code, the files are twice the size the card implies, and nobody from SenseNova has answered a question yet.

Before you call either

Kronos

  1. Clone https://github.com/shiyu-coder/Kronos and pip install -r requirements.txt, then load Kronos.from_pretrained("NeoQuasar/Kronos-small") and KronosTokenizer.from_pretrained("NeoQuasar/Kronos-Tokenizer-base") and wrap them in KronosPredictor
  2. Pair Kronos-mini with Kronos-Tokenizer-2k and Kronos-small or Kronos-base with Kronos-Tokenizer-base, the cards' pairing
  3. The examples read examples/data/XSHG_5min_600977.csv, which no longer exists; point them at tests/data/regression_input.csv, 2,500 five-minute bars
  4. Keep the lookback at or under max_context, 512 bars, and pass the future timestamps you want as y_timestamp, since the calendar fields come from them
  5. Raise sample_count for a steadier forecast, but expect only the mean back; call the lower-level auto_regressive_inference yourself if you need the paths
  6. Treat forecasts as model output to check, not signals; the README says its own backtest pipeline isn't a production trading system

SenseNova-Loop-9B-Preview

  1. Read modeling_sensenova_loop.py before you load it. trust_remote_code runs it
  2. Pin transformers 5.18.0, the version the card checked
  3. Load with dtype=torch.bfloat16 as the card does, or the 38 GB of F32 weights stay at full size
  4. Pass enable_thinking=False to apply_chat_template for a direct answer
  5. Tool calls come back as tool_call blocks with function and parameter tags. Parse them yourself, since no runtime ships a parser
  6. Wait for the vLLM or SGLang pull request to land in a release before putting it behind an API

Questions

Which is better for AI agents, Kronos or SenseNova-Loop-9B-Preview?

Kronos scores 55.2 (C) on agent readiness against SenseNova-Loop-9B-Preview's 46.8 (D), and leads in 2 of 4 scored categories.

Other comparisons with Kronos or SenseNova-Loop-9B-Preview

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report