Does Qwen3.6 35B A3B FP8 support zero data retention?

Yes. Qwen3.6 35B A3B FP8 is available with zero data retention by default on Evroc through the Opper gateway.

Where is Qwen3.6 35B A3B FP8 hosted?

Qwen3.6 35B A3B FP8 runs on EU hosting routes through the Opper gateway, with contractually enforced residency on supported providers.

Is Qwen3.6 35B A3B FP8 trained on prompts and outputs?

No. Every hosting route for Qwen3.6 35B A3B FP8 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen3.6 35B A3B FP8?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen3.6 35B A3B FP8. Contact hello@opper.click to receive it.

Qwen3.6 35B A3B FP8

by Alibaba

Qwen3.6 35B A3B FP8 is a fine-grained FP8-quantized variant of the Qwen3.6 35B A3B sparse Mixture-of-Experts model, carrying 35 billion total parameters with 3 billion activated and performance metrics nearly identical to the original. It uses block-size 128 quantization to lower the memory footprint while preserving reasoning and coding capability. The model supports text, image, and video inputs, with improved agentic coding and an option to retain reasoning context from prior messages for iterative development. It keeps the same 262,144 token native context window as the base model. It is a fit for cost-conscious inference and resource-constrained environments where quantized quality is sufficient, while still supporting tool calling, thinking mode, and structured outputs.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

—

Max output

—

Input price

$0.34 /1M

Output price

$1.37 /1M

EU residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Qwen3.6 35B A3B FP8 runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
Evroc	EU	Zero data retention	No	$0.34	$1.37

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Qwen3.6 35B A3B FP8 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Evroc — Sweden🇸🇪

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EU; DPA available.

Zero data retention: On by default on Pay-as-you-go.
Training: No training on customer data.
Logging: Abuse monitoring
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Get started

Call Qwen3.6 35B A3B FP8 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.click/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "evroc/Qwen/Qwen3.6-35B-A3B-FP8",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);