mr-r0b0t - r0b0tlab
- 104 followers
- United States of America
- @mr_r0b0t
Popular repositories Loading
-
hermes-zvec-memory
hermes-zvec-memory PublicLocal-first Hermes memory provider on zvec-grep (hybrid BM25+vector RRF over Markdown vault)
-
hermes-concurrent-agents
hermes-concurrent-agents PublicDeploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordinated, crash-recovering.
-
hermes-buzz-shared-profile
hermes-buzz-shared-profile PublicmacOS Hermes skill for sharing one canonical writable profile across Buzz and ACP surfaces
-
DeepSeek-V4-Flash-DSpark-v026-SM121
DeepSeek-V4-Flash-DSpark-v026-SM121 PublicDeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, DSpark K6)
-
llm-wiki_obsidian_hermes_r0b0tlabbra1n
llm-wiki_obsidian_hermes_r0b0tlabbra1n PublicFilesystem-first LLM-Wiki + Obsidian + Hermes Agent memory system. Markdown source of truth, SQLite FTS5 search, secret scanning, tier-based memory. Built for local LLM setups.
-
qwen38-27b-nvfp4-sm121-vllm
qwen38-27b-nvfp4-sm121-vllm PublicQwen3.8-27B NVFP4 (W4A16 shipped recipe) + MTP on NVIDIA DGX Spark GB10/SM121 — vLLM v0.27.2rc0, FP8 KV, 262K context, full reproducibility pack
Repositories
- hermes-zvec-memory Public
Local-first Hermes memory provider on zvec-grep (hybrid BM25+vector RRF over Markdown vault)
- mimo26-nvfp4-sm121 Public
MiMo-V2.6-Flash-RL NVFP4 (hybrid FP8-KV) on 2x GB10/SM121 — SGLang + DFlash, TP=2 across two DGX Sparks
- glm53-flash-exl3-dflash2-sm121 Public
vLLM EXL3 runtime for GLM-5.3-Flash on DGX Spark / GB10 (SM121): fused EXL3 MoE kernels, DFlash2 speculative decoding, measured receipts
- hermes-r0b0t-vibeCAD Public
- atlas Public
WIP: r0b0tlab Atlas fork carrying active GB10/SM121 and Nemotron 3.5 Lightning + DSpark development; not a qualified release
- buun-llama-qwen3.8-27b-exl3-4.00bpw Public
Qwen3.8-27B EXL3 + DFlash2 on buun-llama-cpp. Eval twin of qwen38-exl3-dflash2. Private until gates complete.
- qwen38-exl3-dflash2 Public
Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090
- exllamav3 Public Forked from turboderp-org/exllamav3
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
- qwen38-flashnext-exl3 Public
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…