motif64

All capsules

7 capsules, newest first

Tags, all of them
dgx-spark
Clear

Selects and tags apply at once. Press / to jump to the words.

  • m64_ca3a28a8569eAgents · ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF · Strata · GB10 · 82 GB VRAM

    opencode on Qwen3.8-Flash-Next IQ3_S, local (Strata, GB10). opencode 1.18.23 (sst/opencode), driven through `opencode serve`, with Qwen3.8-Flash-Next (Qwen's 125B-A6B MoE, ISTA-DASLab's GSQ-RCO IQ3_S GGUF) served by Strata 0.2.13's DGX Spark engine in the same container: 262144-token context, MTP drafting, pictures on. Each session gets an empty directory; the agent can write and run code there, and every tool call is reported. Asks for no network: prompts and code stay on this machine.

  • m64_0f5b8210b0a4Agents · ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF · Strata · GB10 · 82 GB VRAM

    pi coding agent on Qwen3.8-Flash-Next IQ3_S, local (Strata, GB10). pi coding agent 0.73.1 (badlogic/pi-mono), driven through `pi -p --mode json`, with Qwen3.8-Flash-Next (Qwen's 125B-A6B MoE, ISTA-DASLab's GSQ-RCO IQ3_S GGUF) served by Strata 0.2.13's DGX Spark engine in the same container: 262144-token context, MTP drafting, pictures on. Each session gets an empty directory; the agent can write and run code there, and every tool call is reported. Asks for no network: prompts and code stay on this machine.

  • m64_f51e8491f6d5Chat · ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF · llama.cpp · GB10 · 80 GB VRAM

    Qwen3.8-Flash-Next IQ3_S on llama.cpp v1.0.0 (GB10). A local OpenAI-compatible chat endpoint for Qwen3.8-Flash-Next (Qwen's 125B-A6B MoE, ISTA-DASLab's GSQ-RCO IQ3_S GGUF) on stock llama.cpp v1.0.0 built with CUDA 13 for sm_121, 256K context. Reads images, streams, tool calls. Needs no network.

  • m64_5deb4065b1cfChat · ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF · llama.cpp · GB10 · 80 GB VRAM

    Qwen3.8-Flash-Next IQ3_S on llama.cpp v1.0.0 (GB10). A local OpenAI-compatible chat endpoint for Qwen3.8-Flash-Next (Qwen's 125B-A6B MoE, ISTA-DASLab's GSQ-RCO IQ3_S GGUF) on stock llama.cpp v1.0.0 built with CUDA 13 for sm_121, 256K context. Reads images, streams, tool calls. Needs no network.

  • m64_ef24b3f62fa7Chat · ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF · llama.cpp · GB10 · 72 GB VRAM

    Qwen3.8-Flash-Next IQ3_S on llama.cpp v1.0.0 (GB10). A local OpenAI-compatible chat endpoint for Qwen3.8-Flash-Next (Qwen's 125B-A6B MoE, ISTA-DASLab's GSQ-RCO IQ3_S GGUF) on stock llama.cpp v1.0.0 built with CUDA 13 for sm_121, 64K context. Reads images, streams, tool calls. Needs no network.

  • m64_c2cef7905f1bImage generation · chatrlabs/Qwen-Image-2.1-Uncensored-Omni-Quantized · diffusers · GB10 · 56 GB VRAM

    Qwen-Image-2.1 Uncensored Omni text-to-image on GB10 (diffusers). ChatR Labs' uncensored Omni adapter (step 90,000, merged into Qwen's 7B Qwen-Image-2.1 at strength 1.0, BF16) at 1024x1024, 35 steps, true CFG 5.0, the model card's settings. Can produce adult content. Qwen Research License: non-commercial use only. Runs fully offline.

  • m64_8b0f715a688cChat · Qwen3.8-Flash-Next IQ3_S · Strata · GB10 · 72 GB VRAM

    Qwen3.8-Flash-Next IQ3_S on Strata (GB10). A local OpenAI-compatible chat endpoint for Qwen3.8-Flash-Next (Qwen's 125B-A6B MoE, ISTA-DASLab's GSQ-RCO IQ3_S GGUF) on Strata 0.2.13's DGX Spark engine, 64K context, with the MTP draft layer. Reads images, streams, tool calls. Needs no network.