From pages to possibilities.
Extract readable Markdown from PDFs and images. Entirely on your machine.
Your document, page by page
Drop a PDF or images above to preview and extract their contents.
Fast mode uses deterministic selection. MTP status is confirmed after generation. Output must fit the remaining context. Changing LM head precision reloads the model on the next request and may repeat warmup. INT8/INT4 require single-GPU CUDA, FP16/BF16 and an unquantized, bias-free head. Quantization can change output.
Make yourself understood.
Thoughtful translation. Entirely on your machine.
Bring your words with you.
Import text, subtitles, JSON, DOCX or PDF. Document imports extract text locally; downloads are plain text, without the original document layout.
TXT · MD · SRT · VTT · JSON · DOCX · PDF / up to 8 files, 80,000 characters eachWords worth keeping.
Recent work and your phrasebook, stored only in this browser.
A little knowledge goes a long way.
Ask your documents. Follow the evidence.
Every token, in perspective.
Live hardware readings and measured requests from this workspace.
Decode performance
Recent workspace requests · tok/sRecent requests
Exact generated IDs, including EOS| Model / status | Input | Output | First token | Decode | MTP |
|---|---|---|---|---|---|
| No requests yet. Start a conversation to see real measurements. | |||||
Decode speed excludes the first token, prefill, warmup, and final output processing. Hardware readings are sampled separately every two seconds. API requests outside this workspace are not listed.
Put your setup to the test.
A repeatable, local check of generation speed.
A small test. A clear result.
One warmup followed by three measured requests. Uses the selected model and generation mode, with a 128-token output limit.
- Real token counts from the inference worker
- Median decode speed and first-token latency
- Hardware and settings recorded with results
The first warmup can take several minutes.
Run a benchmark to measure your model.
This measures post-first-token decode speed, not whole-request throughput. Requests that stop before 128 output tokens are shown but excluded from the fixed-length median. Compare systems using the same prompt, model, context, output length, and stopping policy.
One engine. Many possibilities.
Use your local Eole server from other applications.
OpenAI-compatible connection
Point your client at this address and select a configured model.
Chat Completions · Responses API · Anthropic Messages
A quick example
About this workspace
Chats live in this browser's local storage. Clear browser data to remove them. Knowledge collections are temporary server-memory data, isolated by tab session. The server also retains the last 50 workspace request metrics in memory.