Model page

Qwen/Qwen3.6-35B-A3B warn

downloads 5.6Mlikes 2.7klicense apache-2.0arch qwen3_5_moeparams 35951.8Mupdated 2026-04-24

chat template: present · view on Hugging Face ↗

Ingot findings

Static battery clean: safetensors weights, license declared, no template/tokenizer drift detected. Deep battery not yet run. Weights battery: embedding-norm scan over 248320 tokens (BF16, 2048-dim) found 1116 undertrained candidates, 341 plain-ASCII. Scanned 2026-08-20 (published from a community scan).

medium Undertrained (glitch) token surface in vocabulary

Embedding-norm scan flagged 1116 undertrained tokens (norm < 0.3× the vocabulary median of 0.567), including 341 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "tedothi", "ForCanBeConvertedToF", "ForCanBeConverted", "szexf", "Kinhted", "xfabl", "PostalCodesNL", "useRalative". In models where this class was tested behaviorally, such tokens silently rewrote user input into confident, schema-valid, wrong output. These are candidates from the weights alone; behavioral confirmation requires the GPU deep battery.

How to fixruntime guardweight-level

Keep the affected token strings out of the model's input — the scan-derived runtime guard carries this model's exact blocklist.

  1. Fetch this model's guard artifact (`/api/v1/guard/<owner>/<model>`): the confirmed corrupting tokens and the low-norm candidate list, derived from the published scan.
  2. Screen inbound text with it (the `@ingotai/guard` package is a reference implementation) and route flagged records to a different model or human review — verbatim-copy tasks on flagged strings are the failure mode.
  3. The underlying cause is undertrained embeddings in the weights; a true fix is weight-level (continued pretraining on the affected tokens) — that is not a patch, it's a training job.

Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.

Fingerprint

The durable weights-and-metadata profile of this model, rebuilt on every scan and deep-battery run. Updated 2026-08-20.

architectureqwen3_5_moe
parameters35951.8M
vocabulary248,320 tokens
licenseapache-2.0
serializationsafetensors
chat templatepresent · sha256:e84f32a23fdda276
glitch-token surface1,116 undertrained candidates, 341 plain-ASCII
Full fingerprint
architecturesQwen3_5MoeForConditionalGeneration
librarytransformers
pipelineimage-text-to-text
repo files40
revision995ad96eacd9
HF snapshot5.7M downloads · 2.7k likes · updated 2026-04-24 · captured 2026-08-20
embedding tensormodel.language_model.embed_tokens.weight · BF16 · 248,320×2048
embedding normsmedian 0.5666 · mean 0.5547
lineage checkno claimed base model
glitch-token samples"tedothi", "ForCanBeConvertedToF", "ForCanBeConverted", "szexf", "Kinhted", "xfabl", "PostalCodesNL", "useRalative", "tarsker", "useRal", "ejahter", "echslungs"

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: warn

[![Ingot scan](https://ingot.tools/api/v1/models/Qwen/Qwen3.6-35B-A3B/badge.svg)](https://ingot.tools/models/Qwen/Qwen3.6-35B-A3B)
Gate it in CI