Model page

Qwen/Qwen3-32B warn

downloads 3.5Mlikes 737license apache-2.0arch qwen3params 32762.1Mupdated 2025-07-26

chat template: present · view on Hugging Face ↗

Scan coverage

Ingot runs three batteries against a model. What each one checks →

BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-22
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-22151,936-token embedding scanned · 3195 undertrained
Behavioral batteryLive-inference differentialsnot run

Findings

Scanned 2026-08-22 · published from a community scan.

medium Undertrained (glitch) token surface in vocabulary

Embedding-norm scan flagged 3195 undertrained tokens (norm < 0.3× the vocabulary median of 1.336), including 113 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "$PostalCodesNL", "ForCanBeConvertedToF", "PostalCodesNL", "ForCanBeConverted", "useRalative", "useRal", "thuisontvangst", "webElementX". 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 behavioral 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 profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-22.

architectureqwen3 · 64 layers · 5120-dim
parameters32762.1M
vocabulary151,936 tokens
licenseapache-2.0
serializationsafetensors
chat templatepresent · sha256:a55ee1b1660128b7
glitch-token surface3,195 undertrained candidates, 113 plain-ASCII
Full measured fingerprint
architecturesQwen3ForCausalLM
librarytransformers
pipelinetext-generation
repo files27
revision9216db5781bf
HF snapshot3.6M downloads · 736 likes · updated 2025-07-26 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · BF16 · 151,936×5120
embedding normsmedian 1.3365 · mean 1.2745
lineage checkno claimed base model
glitch-token samples"$PostalCodesNL", "ForCanBeConvertedToF", "PostalCodesNL", "ForCanBeConverted", "useRalative", "useRal", "thuisontvangst", "webElementX", "sexkontakte", "wannonce", "swingerclub", "sextreffen"

Battery runs

The run trace behind the findings above: every deep-battery job for this model, with what each run measured or why it failed. Findings are only as good as the runs that produced them.

batterystatusqueueddurationattempts
gpucomplete2026-08-22 00:415m1
gpufailed2026-08-22 00:232m1
gpufailed2026-08-21 21:323m1
weightscomplete2026-08-21 07:4232s1
gpu run 2026-08-22 measurements
probes runglitch
gpu run 2026-08-22 error detail

Traceback (most recent call last): | raise ValueError( | ValueError: To serve at least one request with the models's max seq len (8192), (2.00 GiB KV cache is needed, which is larger than the available KV cache memory (0.49 GiB). Based on the available memory, the estimated maximum model length is 1984. Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine. | Traceback (most recent call last): | raise RuntimeError("Engine core initialization f

gpu run 2026-08-21 error detail

Traceback (most recent call last): | OSError: I/O error: IO Error: No space left on device (os error 28)

weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · BF16 · 151,936×5120
glitch surface3,195 undertrained, 113 plain-ASCII
lineage checknot checked (no claimed base model)

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/Qwen3-32B/badge.svg)](https://ingot.tools/models/Qwen/Qwen3-32B)
Gate it in CI