Model page

Qwen/Qwen3.5-122B-A10B-GPTQ-Int4 warn

Glitch tokens that can silently corrupt ordinary input.

downloads 377.6klikes 53license apache-2.0arch qwen3_5_moeparams 125086.5Mupdated 2026-04-24

chat template: present · view on Hugging Face ↗

Scan coverageStatic battery2026-08-22Weights battery2026-08-22Behavioral batterynot rundetails

Battery	Looks at	Status
Static battery	Metadata & packaging	complete 2026-08-22
Weights battery	Weights forensics: no GPU, no download	complete 2026-08-22248,320-token embedding scanned · 1561 undertrained
Behavioral battery	Live-inference differentials	not run

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

Findings

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

medium Undertrained (glitch) token surface in vocabulary

Embedding-norm scan flagged 1561 undertrained tokens (norm < 0.3× the vocabulary median of 0.665), including 395 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "tedothi", "ForCanBeConverted", "ForCanBeConvertedToF", "szexf", "Kinhted", "PostalCodesNL", "xfabl", "tarsker". 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.

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.
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.
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.

Put this result in your workflow

Check every checkpoint before it ships

Use the web app, API, CLI, or CI gate to scan candidate checkpoints and catch model drift before deployment. Public-model scans publish to the open database; paid plans add the volume needed for continuous checks.

Create a free account Need private scans?Compare plans

Fingerprint

The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-22.

architecture	qwen3_5_moe
parameters	125086.5M
vocabulary	248,320 tokens
license	apache-2.0
serialization	safetensors
chat template	present · sha256:a4aee8afcf2e0711
glitch-token surface	1,561 undertrained candidates, 395 plain-ASCII

Full measured fingerprint

architectures	Qwen3_5MoeForConditionalGeneration
library	transformers
pipeline	image-text-to-text
repo files	53
revision	30cd92cba970
HF snapshot	626.3k downloads · 50 likes · updated 2026-04-24 · captured 2026-08-21
embedding tensor	model.language_model.embed_tokens.weight · BF16 · 248,320×3072
embedding norms	median 0.665 · mean 0.6592
lineage check	no claimed base model
glitch-token samples	"tedothi", "ForCanBeConverted", "ForCanBeConvertedToF", "szexf", "Kinhted", "PostalCodesNL", "xfabl", "tarsker", "useRalative", "tarskereso", "useRal", "ejahter"

Battery runs (1)the run trace behind the findings — what each job measured

battery	status	queued	duration	attempts
weights	complete	2026-08-21 07:43	38s	1

weights run 2026-08-21 — measurements

probes run	glitch-norm-scan, lineage-norm-correlation
embedding tensor	model.language_model.embed_tokens.weight · BF16 · 248,320×3072
glitch surface	1,561 undertrained, 395 plain-ASCII
lineage check	not checked (no claimed base model)

Verdict badge

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

[![Ingot scan](https://ingot.tools/api/v1/models/Qwen/Qwen3.5-122B-A10B-GPTQ-Int4/badge.svg)](https://ingot.tools/models/Qwen/Qwen3.5-122B-A10B-GPTQ-Int4)

Gate it in CI