GLM-5.2-NVFP4-REAP-469B serving on SM120 (4× RTX PRO 6000 Blackwell) — one-command vLLM launch recipe, 250K context, DeepSeek Sparse Attention + MTP speculative decode
☆155Jun 19, 2026Updated 4 months ago
Alternatives and similar repositories for glm-5.2-sm120
Users that are interested in glm-5.2-sm120 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- GLM-5.2 UD-Q2 decode speedup: CPU∥GPU MoE expert-split (harness, specs, de-risk)☆23Aug 9, 2026Updated 2 months ago
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆108Aug 20, 2026Updated 2 months ago
- Serve GLM-5.2 469B (REAP-pruned, NVFP4) across 3× NVIDIA DGX Spark with vLLM pipeline parallelism — 256K context, production-ready config…☆34Jul 12, 2026Updated 3 months ago
- Educational reference: NVIDIA Blackwell SM100 vs SM120, NVFP4, tcgen05, MoE inference on consumer Blackwell☆29Sep 3, 2026Updated 2 months ago
- Validated GLM-5.3 Flash recipe for 2x NVIDIA RTX PRO 6000 Blackwell 96GB: 262K context, EXL3/TR3, adaptive MTP, tools, and vision.☆62Sep 20, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- GLM-5.2 QuantTrio TP=4+DCP2 on 4x NVIDIA DGX Spark (GB10) — tuned and measured under a real agent workload. Adaptive MTP, the indexer law…☆20Aug 24, 2026Updated 2 months ago
- NVFP4 KV cache for vLLM on SM120 (RTX PRO 6000) via FlashInfer FA2 explicit-SF-stride patch — ~1.5x fp8 pool at ~95-104% speed☆20Jun 5, 2026Updated 5 months ago
- Linux-native Touch ID for Intel Macs with Apple's T2 chip through fprintd. Early Omarchy proof of concept, validated on MacBookPro16,1.☆15Updated this week
- A locally running AI image blocker for Chrome☆46Aug 31, 2026Updated 2 months ago
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,840Oct 26, 2026Updated last week
- Truthful scheduler-step and streaming visualization for local LLM inference☆35Sep 6, 2026Updated 2 months ago
- MiMo-V2.5 NVFP4 4-bit weights + NVFP4 4-bit KV cache + DFlash speculative decoding on 2× NVIDIA DGX Spark — 1M context, 3.4M-token KV poo…☆18Jul 13, 2026Updated 3 months ago
- RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink☆1,186Updated this week
- Autonomous self-improving 4x DGX Spark (GB10) MoA stack + LoRA loop (DSV4F router, Qwen3.6/Omni/TwoTower/Gemma). Hermes MoA routing, ~90%…☆24Aug 17, 2026Updated 2 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Notification integration for SimpleX messenger☆23Oct 19, 2026Updated 2 weeks ago
- DeepSeek-V4-Flash W4A16-FP8 quantization on 8x H200 — patches, recipe, mission report☆14Sep 26, 2026Updated last month
- ☆37Apr 26, 2026Updated 6 months ago
- AEON vLLM Ultimate — vLLM 0.27.1 built from source for DGX Spark / Blackwell (sm_121a/GB10). DSpark quantized Markov heads, DFlash SWA on…☆148Oct 6, 2026Updated last month
- Pipeline-parallel LLM inference across GPUs on separate machines.☆469Oct 28, 2026Updated last week
- Core IaaS engine and cloud infrastructure foundation of ZSvirt☆15Aug 12, 2026Updated 2 months ago
- GLM-5.3-Flash (320B MoE) at TP4 across four DGX Sparks, same day as the model drop: 36 tok/s, 1.26M-token FP8 KV pool, 262K context, MTP …☆57Oct 10, 2026Updated 3 weeks ago
- GLM-5.2 (744B/40B MoE) on a 4× DGX Spark / GB10 (sm_121) cluster: portable Triton sparse-MLA kernels, a data-free expert prune, MTP draft…☆37Aug 20, 2026Updated 2 months ago
- Live dashboard: fire N parallel streaming coding-agent runs at any OpenAI-compatible endpoint — per-run TTFT/tok-s/E2E, real kill switch,…☆27Jul 23, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- instant copy-on-write repo forks with forked agent chats - fork the repo AND the conversation in one second☆18Jun 12, 2026Updated 4 months ago
- Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesses · vision · audi…☆25Oct 6, 2026Updated last month
- Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster☆77Jul 25, 2026Updated 3 months ago
- ☆14Aug 12, 2026Updated 2 months ago
- my version of the models dev site which is way faster and has the filters I want☆18Apr 22, 2026Updated 6 months ago
- ☆14Oct 14, 2026Updated 3 weeks ago
- GLM 5.3 Flash for 2x RTX 6000, Full Mixed EXL3 Support, Code C1 >220tps☆22Oct 25, 2026Updated last week
- Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.☆270Oct 6, 2026Updated last month
- ☆15Jun 17, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Capture, inspect, and replay webhooks with 90-day history + signature verification. Built on Cloudflare Workers + D1.☆16Feb 17, 2026Updated 8 months ago
- Security capability evaluation of locally served models. Method, corpus, and per-model results.☆18Oct 19, 2026Updated 2 weeks ago
- A DSPy port of PEEK☆44May 25, 2026Updated 5 months ago
- Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and …☆568Updated this week
- Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker…☆166Oct 22, 2026Updated 2 weeks ago
- MiniMax-M3 (428B, no pruning) at 36 tok/s on 2× NVIDIA DGX Spark — W4A16 GPTQ + NVFP4 KV + EAGLE-3 speculative decoding on vLLM. Three se…☆45Jul 13, 2026Updated 3 months ago
- Validated vLLM recipe: Qwen3.8-27B-NVFP4 at full 262,144-token context on a single RTX 5090, GPU-only (no CPU offload).☆16Aug 20, 2026Updated 2 months ago