Model page

t-firefly/qwen3-8b-rknn3-rk1828 warn

Weights only ship in a format that can run code when loaded. Plus 1 minor note.

downloads 282likes 1license apache-2.0arch qwen3updated 2026-08-20

claims base: Qwen/Qwen3-8B · chat template: present · view on Hugging Face ↗

Scan coverageStatic battery2026-08-21Weights battery2026-08-21Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-21
Weights batteryWeights forensics: no GPU, no downloadcomplete 2026-08-21no token vocabulary — pickle audit only · pickle audit clean
Behavioral batteryLive-inference differentialsnot run

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

Findings

Scanned 2026-08-21 · published from a community scan.

medium Pickle-serialized weights, no safetensors

Weights ship only as pickle-based files (Qwen3-8B.embed.bin). Loading pickle executes arbitrary code from the file — prefer a safetensors release or load in a sandbox.

How to fix

Convert the weights to safetensors before loading them anywhere that matters.

  1. Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
  2. Convert locally in a sandbox: `pip install safetensors` and use `safetensors.torch.save_file` on a state dict loaded with `torch.load(..., weights_only=True)` (refuses most code-execution payloads), or use Hugging Face's `convert.py` space/script.
  3. Pin the exact revision hash you converted from, and load only your converted safetensors artifact from then on.

info Pickle static analysis clean

Opcode-level parse of Qwen3-8B.embed.bin (no code executed) found only standard serialization globals (0 distinct, all torch/collections/numpy). Pickle remains an executable format — this verifies the current bytes, not future uploads; prefer a safetensors release.

low Pickle checkpoint only partially analyzable

Static analysis could not fully parse: Qwen3-8B.embed.bin: legacy parse stopped after 0 pickle(s): truncated pickle. Unparsed content is unverified.

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.

Fingerprint

The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-21.

architectureqwen3 · 36 layers · 4096-dim
vocabulary151,936 tokens
licenseapache-2.0
serializationgguf pickle
chat templatepresent · sha256:a55ee1b1660128b7
claimed lineageQwen/Qwen3-8B
lineage verifiedunverified — weights battery pending
Full measured fingerprint
architecturesQwen3ForCausalLM
pipelinetext-generation
repo files11 — pickle: Qwen3-8B.embed.bin
revision82408b8e2226
HF snapshot922 downloads · 1 likes · updated 2026-08-20 · captured 2026-08-21
weights batterytoken-embedding scan n/a — no token-embedding tensor found in the pickle checkpoint(s) — pickle checkpoint(s) statically analyzed anyway
pickle auditQwen3-8B.embed.bin — 0 standard global(s) · legacy (pre-1.6) format, head-scan only
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-21 05:135s1
weights run 2026-08-21 — measurements
probes runpickle-static-analysis

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/t-firefly/qwen3-8b-rknn3-rk1828/badge.svg)](https://ingot.tools/models/t-firefly/qwen3-8b-rknn3-rk1828)
Gate it in CI