nvidia/Gemma-4-31B-IT-NVFP4 warn
claims base: google/gemma-4-31B-it · chat template: present · view on Hugging Face ↗
Scan coverage
Ingot runs three batteries against a model. What each one checks →
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-22 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-22262,144-token embedding scanned · 0 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | not run |
Findings
Scanned 2026-08-22 · published from a community scan.
medium License differs from claimed parent (other vs apache-2.0)
This model declares other while its claimed base google/gemma-4-31B-it declares apache-2.0. Verify the re-license is permitted before commercial use.
How to fix
Verify the re-license is actually permitted before relying on it.
- Read the parent's license for derivative-work and re-licensing terms — many open-weight licenses (e.g. Llama-family) do not permit arbitrary re-licensing.
- If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.119). The glitch-token data-corruption class has no candidate surface in this model.
info Weights consistent with claimed parent google/gemma-4-31B-it
Mean cosine similarity of 64 sampled token-embedding rows against google/gemma-4-31B-it is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).
How to fix
Fix or verify the `base_model` declaration so lineage checks can run.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.
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.
| architecture | gemma4 |
| parameters | 20868.6M |
| vocabulary | 262,144 tokens |
| license | other |
| serialization | safetensors |
| chat template | none |
| claimed lineage | google/gemma-4-31B-it |
| lineage verified | consistent vs google/gemma-4-31B-it — embedding-row cosine 1.000 |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | Gemma4ForConditionalGeneration |
| library | Model Optimizer |
| pipeline | text-generation |
| repo files | 15 |
| revision | 4135a98a9b72 |
| HF snapshot | 2.4M downloads · 558 likes · updated 2026-07-13 · captured 2026-08-21 |
| embedding tensor | model.language_model.embed_tokens.weight · BF16 · 262,144×5376 |
| embedding norms | median 1.1186 · mean 1.1182 |
| lineage check | consistent — cosine 1 over 64 sampled rows vs google/gemma-4-31B-it |
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.
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 07:42 | 3m | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.language_model.embed_tokens.weight · BF16 · 262,144×5376 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 1 over 64 rows vs google/gemma-4-31B-it |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/nvidia/Gemma-4-31B-IT-NVFP4)