Text Generation
Output
Idle
Relative perplexity
low
med
high
Proof Console
Side-by-side translation compare
Same source, different models and engines. Compare quality and latency.
Show benchmark receipts
Artifact id
Pending
Browser / device
Awaiting run
Saved receipts
0
No benchmark receipts linked yet.
Evidence snapshot
No receipt loaded
Teacher BLEU
--
Student BLEU
--
Teacher chrF
--
Student chrF
--
Size delta
--
Artifact link
Pending
Sample panel
Deterministic smoke panel
Left
baseline
Reference lane
Pinned baseline.
Status
Idle
Model size--
Load--
First token--
Decode--
Total--
DeviceWebGPU
Output
No run yet
Awaiting compare run.
Right
student
Challenger lane
Swap engine or model.
Status
Idle
Model size--
Load--
First token--
Decode--
Total--
DeviceWebGPU
Output
No run yet
Awaiting compare run.
Image Generation
Setup required
Output
Idle
Verify
Setup required
Idle
No output yet.
Raw JSON
No JSON yet.
Advanced
Profile: profiles/verbose-trace
Intent
--
Resolved Graph
Candidate Matches
Proposal JSON
No proposal loaded.
Runtime Overlay
Model Intake
Import pre-converted RDRR from base URL
Advanced
Models & Storage
Storage
OPFS usage
-- / --
GPU Info
Device
--
System RAM
--
Buffer Limit
--
Features
--
Unified memory: GPU shares system RAM
Diagnostics Stats
GPU Memory (tracked)
Tracked GPU
--
Peak GPU
--
Buffers
--
Requested
--
Pool hit rate
--
Max buffer
--
Top buffers (tracked)
[?]
No tracked buffers yet.
JS / CPU
JS Heap
--
System RAM (est)
--
Swap
Not available
Storage (OPFS)
OPFS usage
--
Active model
--
Memory Control
Run Controls
Setup required
Reference docs — 3 of 9 sampled each run
Ranked by cosine similarity to your query.
Generation settings
auto: --
auto: --
auto: --
auto: --
Xray panels
Profiling
Runtime
Diffusion Controls
0/2048
Advanced
0/1024
Inference Pulse
Performance
Tokens/sec
--
TTFT
--
Prefill
--
End-to-end
--
Decode
--
Prompt / Gen
--
Recent Runs
Run
TTFT
Prefill
Decode
E2E
KV Cache
Allocated
--
Used
--
Efficiency
--
Seq / Max
--
Layout
--