stealthmodels.

MODEL FIELD GUIDE

Qwen3.5 9B: Ground Truth

A compact, Apache-2.0 multimodal model with Q4 weight files around 5–6 GB, making local deployment practical on smaller machines.

Drawn by this model01 / 01
Ground Truth benchmark result generated by this model
SVG BENCHMARKGround TruthView result

A good fit for

Local assistants, document and image understanding, and lightweight tool workflows on consumer hardware.

Context window
1,010,000tokens[3]
Active parameters
9BparametersEstimated[3]
License
Apache-2.0[1]
Model factsArchitecture, context & capabilities
Developer
Qwen[1]
Origin
China (Alibaba Group/Qwen organization context)[2]
Family
Qwen 3.5[1]
Context window
1,010,000 tokens[3]
Architecture
Dense causal language model with vision encoder; Gated DeltaNet + gated attention; MTP-trained[1] [3]
Total parameters
9B[3]
Active parameters per token
9BEstimated[3]
Input
text, image, video[1] [3]
Output
text[1] [3]
API access & pricingOpenRouter · $0.1 input / $0.15 output · per 1M tokens
  • OpenRouterObserved 2026-10-06
    Input $0.1Output $0.15

    per 1M tokens

    qwen/qwen3.5-9b[4]
Run it locallyWeights, memory & deployment

consumer/workstation

[1] [3]
  • Unsloth Q8_0 GGUF9.53 GB storage · 8-bit[3]
  • Unsloth BF16 GGUF17.9 GB storage · BF16[3]
  • Multimodal projector0.92 GB storage · BF16[3]
Measurements & sources5 primary references · Speed & serving conditions

StealthMark score

StealthMark measures fluid and visual intelligence of AI models.

General and Visual

General Intelligence

Perspective, anatomy, correct shadows, purposeful detail and physical consistency.

Visual Intelligence

Likeness, anatomy, detail, light, materials, composition and artistic expression.

Judging

Frontier Models blindly judge the AI generation unbiased through an intricate process. Our researchers control for mistakes.

Overall score

Overall combines weighted task scores on a scale from 0 to 100. Repeating a task does not increase its weight. Estimated means the total includes an estimate for one missing scene.

Benchmaxxing

Benchmaxx flags models that score unusually well on the familiar Pelican task compared with their other benchmark results. The percentage measures that imbalance, not the probability of training contamination. Flagged Pelican scores are excluded from Overall. Pelican never counts toward General or Visual.

We keep some prompts private to discourage test-specific optimization.

Scoring categories

Prompt & likeness

Subjects, actions and likeness.

Anatomy & construction

Coherent bodies, joints and machinery.

Space & placement

Perspective, scale and contact.

Light & reflections

Lighting, shadows and reflections.

Purposeful detail

Clear, purposeful small features.

Artistry & character

Composition, expression and drawing skill.

Materials & effects

Surfaces, texture and movement.

Visual integrity

Clean shapes, layers and edges.

BENCHMARK RESULTS

Compare results

This link opens the same results in the same order.

StealthMark benchmark results

Reset benchmark preferences?

Return to the default view, clear comparison selections and restore the advertisement.