LLMVision
Qwen3.8 27B Vision Chat
Ask a question or try a short writing task. Sign in when you send your first message.
Qwen3.8 by Alibaba Cloud; GSQ-RCO by DASLab, IST Austria
Model licenses
Qwen3.8-27B GSQ-RCO IQ2_XS body and tokenizer · Apache-2.0
Retain the original Apache-2.0 licence and copyright/attribution notices, accompany modified files with their change notices, and respect patent termination and trademark limitations. The licence grants commercial use and redistribution; it grants no automatic rights in arbitrary user inputs or generated content.
Qwen3.8 vision encoder/projector, BF16 and Q8_0 · Apache-2.0
Chat with Qwen3.8 27B, and attach a picture when you want it to look. Free vision chat on devices you connect. It is a large model: one strong computer can hold it, or the work splits across machines you add. The first download is large. This is not ChatGPT.
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.
https://cp.meshlabs.cloud/v1/organizations/jobsAuthenticate with X-Organization-Api-Key: msk_your_personal_api_key. The header name matches org keys; personal keys use the same endpoint.
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": "qwen38-27b-gguf-pp",
"job_spec": {
"max_context": 8192,
"kv_hot_window": 32768,
"enable_thinking": true,
"max_new_tokens": 2048,
"prompt": "A photorealistic lighthouse at dusk",
"reasoning_effort": "high",
"vision_max_pixels": 4194304,
"vision_max_tokens": 4096,
"vision_merge_size": 2,
"vision_min_tokens": 256,
"vision_patch_size": 16
}
}job_spec fields
| Field | Required | Default | Description |
|---|---|---|---|
tools | No | — | 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. |
max_context | No | 8192 | Total 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. |
kv_hot_window | No | 32768 | Physical attention KV is capped at the newest N tokens, so a conversation longer than N forgets its oldest turns instead of stopping at the context limit. 0 keeps the full context resident. At or below the context window this changes nothing — same memory, same attention — and lowering it below the context trades long-range recall for unbounded conversation length, because the model genuinely cannot see past the window. |
turns | No | — | 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`. |
enable_thinking | No | true | Enable Thinking |
input_image_url | No | — | Input Image Url |
max_new_tokens | No | 2048 | Max New Tokens |
prompt | Yes | — | Prompt |
reasoning_effort | No | high | Reasoning Effort |
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": "qwen38-27b-gguf-pp",
"job_spec": {
"max_context": 8192,
"kv_hot_window": 32768,
"enable_thinking": true,
"max_new_tokens": 2048,
"prompt": "A photorealistic lighthouse at dusk",
"reasoning_effort": "high",
"vision_max_pixels": 4194304,
"vision_max_tokens": 4096,
"vision_merge_size": 2,
"vision_min_tokens": 256,
"vision_patch_size": 16
}
}'https://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": "qwen38-27b-gguf-pp",
"status": "PENDING",
"job_spec_json": {
"max_context": 8192,
"kv_hot_window": 32768,
"enable_thinking": true,
"max_new_tokens": 2048,
"prompt": "A photorealistic lighthouse at dusk",
"reasoning_effort": "high",
"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": "qwen38-27b-gguf-pp",
"status": "COMPLETED",
"job_spec_json": {
"max_context": 8192,
"kv_hot_window": 32768,
"enable_thinking": true,
"max_new_tokens": 2048,
"prompt": "A photorealistic lighthouse at dusk",
"reasoning_effort": "high",
"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>"
}