LLMVision

Qwen3.8 Flash Next Coder

Ask a question or try a short writing task. Sign in when you send your first message.

Qwen3.8 Flash Next Coder — Coding Assistant

Model licenses

Qwen3.8-Flash-Next · LicenseRef-Qwen-Community-1.0

Qwen Community License 1.0: keep the notice; a licensee over 100M MAU or US$20M monthly revenue must display the model name; a Model-as-a-Service or AI Work Assistant business needs a separate Qwen licence for commercial use. Owner confirmed this condition is handled (2026-11-12).

Distributed license

GSQ-RCO Coder GGUF quantization (ISTA-DASLab) · Apache-2.0

Apache License 2.0. Keep the licence text with the weights. Card declares apache-2.0; the repo publishes no LICENSE file, so the standard text is shipped.

Distributed license

FreeOnlineUnlimitedQwen3.8-Flash-Next API access

Whenever you're ready.

Write your message and press Send to sign in and start.

PNG, JPG, WEBP · up to 25 MB

Describe what you want to build, or paste code and the error it throws, and get code, a fix or a plain-language explanation back. This free AI coding assistant runs Qwen3.8 Flash Next, a 125-billion-parameter mixture-of-experts model that uses about 6 billion parameters per token, in ISTA-DASLab's compressed Coder build. It can read long inputs, such as a large file or several files at once, and you can attach a screenshot. It runs free and unlimited on the devices you connect: this browser, the desktop app, or another computer you own. The first run downloads a large model onto those devices, and a long input takes longer on the first pass. License: Qwen3.8-Flash-Next by Qwen (Alibaba Cloud), Qwen Community License 1.0 (https://huggingface.co/Qwen/Qwen3.8-Flash-Next/blob/de4b8e4d43b917e7706784d8bb445c9af86a3540/LICENSE). Served weights are modified: ISTA-DASLab's GSQ-RCO Coder quantization, split into per-layer stages by Mesh, with the image projector requantized to Q8_0. If you run these weights yourself in a business that offers model access as a service, or an AI coding or office product, the licence asks for a separate licence from Qwen for commercial use.

API reference

Submit via REST

Use your personal API key (msk_…) to create jobs for this workload from your own tools. Jobs started this way run on the same devices you connected on Your Devices — at least one has to be online.

Hide API details
POSThttps://cp.meshlabs.cloud/v1/organizations/jobs

Authenticate with X-Organization-Api-Key: msk_your_personal_api_key. The header name matches org keys; personal keys use the same endpoint.

Input files:Call POST https://cp.meshlabs.cloud/v1/organizations/job-inputs/presign with the same API key, upload your file to the returned upload_url, then pass download_url in job_spec (for example as input_image_url).

Request body

{
  "workload_type": "qwen38-flash-next-coder-gguf-pp",
  "job_spec": {
    "enable_thinking": true,
    "reasoning_effort": "xhigh",
    "max_new_tokens": 2048,
    "max_context": 32768,
    "temperature": 1,
    "top_p": 0.95,
    "top_k": 20,
    "presence_penalty": 0,
    "max_thinking_tokens": 1536,
    "repetition_penalty": 1,
    "speculative_ngram": false,
    "speculative_draft_model": false,
    "speculative_max_draft": 8,
    "min_remote_stages": 0,
    "wire_hidden_dtype": "f16",
    "wire_hidden_codec": "fp16",
    "stage_chaining": true,
    "prompt": "A photorealistic lighthouse at dusk",
    "vision_max_pixels": 4194304,
    "vision_max_tokens": 4096,
    "vision_merge_size": 2,
    "vision_min_tokens": 256,
    "vision_patch_size": 16
  }
}

job_spec fields

FieldRequiredDefaultDescription
system_promptNo—Optional system prompt
toolsNo—Functions the model may call, in the OpenAI format: {"type": "function", "function": {"name", "description", "parameters"}}. A call comes back in the result as tool_calls, each with a name and its arguments. At most 16 tools, 8 KB each and 32 KB in total.
enable_thinkingNotrueThink before answering. Turn off for fast, direct tool calls.
reasoning_effortNoxhighReasoning Effort
max_new_tokensNo2048Maximum generated tokens (thinking + answer). Prompt and generation share the context window.
max_contextNo32768Total tokens the stage hosts allocate KV/recurrent state for — prompt plus generation. The ceiling is the largest context the Oracle measured this model at, so placement never has to extrapolate past evidence. Raising it raises the memory floor and therefore narrows which devices can run the job.
turnsNo—Prior turns of this conversation, oldest first, including the current user message as the final row. Supplying them lets a stage host that still holds this conversation's KV state extend it instead of re-prefilling the whole history. Omit for a single-shot request; the workload then reads `prompt`.
temperatureNo1Temperature
top_pNo0.95Top P
top_kNo20Top K
presence_penaltyNo0Presence Penalty
max_thinking_tokensNo1536Force-close the reasoning block after this many thinking tokens. Must stay meaningfully below `max_new_tokens`: a reasoning budget at or above the total generation budget produces a reply cut off mid-thought with no answer at all. The control plane re-cuts this from the budget the chosen placement can actually afford, so a smaller value is honoured and a larger one is clamped.
repetition_penaltyNo1Repetition Penalty
seedNo—Random seed for reproducibility
speculative_ngramNofalsePrompt-lookup drafting: repeated n-grams from the context are replayed as draft blocks and verified by the model in ONE pass, so a single network round trip can commit several tokens. No extra model; output is identical to sequential decoding.
speculative_draft_modelNofalseRun a tiny GGUF draft model on the checkpoint node to propose draft blocks (prefer 'Draft model bundled filename'; external URL remains available as a fallback). Falls back to n-gram drafting when the draft model is unavailable.
draft_model_fileNo—Filename of an unpartitioned GGUF draft model in this workload bundle. The SDK resolves it from required_files, so private S3 buckets can use the server-provided signed/proxy URL instead of a public URL.
draft_model_urlNo—Optional external HTTPS URL of the tiny GGUF draft model. Used as a fallback when 'Draft model bundled filename' is absent or missing from required_files.
speculative_max_draftNo8Upper bound on draft tokens verified per block. The effective length adapts to the observed acceptance rate.
min_remote_stagesNo0Diagnostic placement knob for GGUF pipeline-parallel testing. When > 0, the checkpoint is assigned only to nodes that would run at least this many stages over WebRTC instead of locally. Falls back after the checkpoint peer grace window to avoid starving production jobs.
wire_hidden_dtypeNof16Hidden activation dtype between GGUF pipeline stages. f16 halves the wire payload for prefill and speculative blocks; f32 is a diagnostic fallback.
wire_hidden_codecNofp16Experimental codec for multi-token hidden activation blocks between GGUF pipeline stages. Single-token decode keeps the cheap dtype path; generic codecs are used only for prefill/speculative blocks where byte savings can offset codec cost. fp16 is safest; auto8/hq8 are diagnostics.
stage_chainingNotrueWhen all GGUF stages are remote and support the chain protocol, send hidden activations directly stage-to-stage instead of relaying each boundary through the checkpoint coordinator.
input_image_urlNo—Input Image Url
promptYes—What to build, or the code and the error

cURL

curl -X POST https://cp.meshlabs.cloud/v1/organizations/jobs \
  -H "X-Organization-Api-Key: msk_your_personal_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "workload_type": "qwen38-flash-next-coder-gguf-pp",
  "job_spec": {
    "enable_thinking": true,
    "reasoning_effort": "xhigh",
    "max_new_tokens": 2048,
    "max_context": 32768,
    "temperature": 1,
    "top_p": 0.95,
    "top_k": 20,
    "presence_penalty": 0,
    "max_thinking_tokens": 1536,
    "repetition_penalty": 1,
    "speculative_ngram": false,
    "speculative_draft_model": false,
    "speculative_max_draft": 8,
    "min_remote_stages": 0,
    "wire_hidden_dtype": "f16",
    "wire_hidden_codec": "fp16",
    "stage_chaining": true,
    "prompt": "A photorealistic lighthouse at dusk",
    "vision_max_pixels": 4194304,
    "vision_max_tokens": 4096,
    "vision_merge_size": 2,
    "vision_min_tokens": 256,
    "vision_patch_size": 16
  }
}'
GEThttps://cp.meshlabs.cloud/v1/organizations/jobs/{job_id}

Poll with the same API key until status is terminal (COMPLETED, FAILED, CANCELED, or MODERATION_BLOCKED). When content moderation is enabled, jobs may start in MODERATION_PENDING before entering the compute queue. Completed jobs include presigned download_url values on each output.

Create response

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "workload_type": "qwen38-flash-next-coder-gguf-pp",
  "status": "PENDING",
  "job_spec_json": {
    "enable_thinking": true,
    "reasoning_effort": "xhigh",
    "max_new_tokens": 2048,
    "max_context": 32768,
    "temperature": 1,
    "top_p": 0.95,
    "top_k": 20,
    "presence_penalty": 0,
    "max_thinking_tokens": 1536,
    "repetition_penalty": 1,
    "speculative_ngram": false,
    "speculative_draft_model": false,
    "speculative_max_draft": 8,
    "min_remote_stages": 0,
    "wire_hidden_dtype": "f16",
    "wire_hidden_codec": "fp16",
    "stage_chaining": true,
    "prompt": "A photorealistic lighthouse at dusk",
    "vision_max_pixels": 4194304,
    "vision_max_tokens": 4096,
    "vision_merge_size": 2,
    "vision_min_tokens": 256,
    "vision_patch_size": 16
  },
  "work_units": [],
  "outputs": [],
  "created_at": "2026-06-08T12:00:00Z",
  "updated_at": "2026-06-08T12:00:00Z"
}

Completed response

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "workload_type": "qwen38-flash-next-coder-gguf-pp",
  "status": "COMPLETED",
  "job_spec_json": {
    "enable_thinking": true,
    "reasoning_effort": "xhigh",
    "max_new_tokens": 2048,
    "max_context": 32768,
    "temperature": 1,
    "top_p": 0.95,
    "top_k": 20,
    "presence_penalty": 0,
    "max_thinking_tokens": 1536,
    "repetition_penalty": 1,
    "speculative_ngram": false,
    "speculative_draft_model": false,
    "speculative_max_draft": 8,
    "min_remote_stages": 0,
    "wire_hidden_dtype": "f16",
    "wire_hidden_codec": "fp16",
    "stage_chaining": true,
    "prompt": "A photorealistic lighthouse at dusk",
    "vision_max_pixels": 4194304,
    "vision_max_tokens": 4096,
    "vision_merge_size": 2,
    "vision_min_tokens": 256,
    "vision_patch_size": 16
  },
  "work_units": [
    {
      "id": "…",
      "index": 0,
      "status": "COMPLETED"
    }
  ],
  "outputs": [
    {
      "id": "…",
      "output_type": "<output type>",
      "filename": "<output filename>",
      "size_bytes": 524288,
      "download_url": "<presigned output download URL>"
    }
  ],
  "created_at": "2026-06-08T12:00:00Z",
  "updated_at": "<completion timestamp>"
}