One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, paired benchmarks, probe tool.
☆363Sep 26, 2026Updated 3 weeks ago
Alternatives and similar repositories for qwen38-mtp
Users that are interested in qwen38-mtp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆41Aug 16, 2026Updated 2 months ago
- Reproduce Lium's LocalMaxxing leaderboard runs (7 boards, 20 Verified) on a rented Lium GPU in one script — vLLM/llama.cpp recipes, measu…☆36Sep 26, 2026Updated 3 weeks ago
- Keeps Spotlight, Siri, Photos analysis, and Apple Intelligence disabled on macOS across updates☆78Aug 23, 2026Updated last month
- GLM-5.3-Flash EXL3 on one 24 GB RTX 3090 + DDR4: elastic GPU expert cache, zero-copy experts, AVX2 CPU tier, OpenAI API☆313Updated this week
- Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.☆68Sep 2, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆77Sep 4, 2026Updated last month
- DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe☆220Sep 24, 2026Updated 3 weeks ago
- Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quan…☆135Updated this week
- Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any …☆90Oct 7, 2026Updated last week
- Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels fo…☆75Sep 2, 2026Updated last month
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆166Sep 3, 2026Updated last month
- Optimized inference for the DGX Spark and spark clusters☆120Updated this week
- An intuitive console agent to fine-tune AI models with little to no experience required!☆209Oct 5, 2026Updated last week
- GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.☆87Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Making sure your context is clean.☆84Oct 11, 2026Updated last week
- Official repository for “GrainSpeech: Less Context, More Detail for Compact Speech Synthesis.”☆58Sep 18, 2026Updated 3 weeks ago
- Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux bu…☆454Updated this week
- Turn your regular JavaScript code into a neural net.☆1,659Updated this week
- Bot Mode for the Hermes desktop: a roster of named agents with their own chats, avatars, routines, and bot-to-bot messaging. Desktop plug…☆668Aug 17, 2026Updated 2 months ago
- Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when …☆2,040Updated this week
- Mirai S (Qwen3.8-27B-S trellis GGUF) on a 12 GB RTX 4070: 262k q8_0 tiered cache, MTP drafting at every depth, harness-proofing, the laye…☆93Updated this week
- Email inbox API for AI agents. Give every agent its own real email address, receive mail as structured webhooks, and reply in-thread over…☆254Updated this week
- vLLM inference solutions for NVIDIA GB10 (DGX Spark, sm121) — KIMI-K3 B12X_MLA + DSpark, GLM-5.2☆67Sep 30, 2026Updated 2 weeks ago
- 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.
- Breaking the quadratic memory barrier in AI☆61Updated this week
- An agentic environment abstraction for Agent Substrate☆67Updated this week
- LLM Inference Engine for Metal and CUDA.☆1,359Updated this week
- 🔎 Username, email & phone OSINT — 9,700+ lookup checks from 19 projects, with profile enrichment, bulk searches, evidence graphs and exp…☆137Updated this week
- LLM inference in C/C++☆56Aug 8, 2026Updated 2 months ago
- GLM-5.2 NVFP4+AQLM on 3× DGX Spark — 380k context MTP serve stack☆72Aug 2, 2026Updated 2 months ago
- MLX (Apple Silicon) port of MiniMax-H3 — 33B joint video+audio diffusion. Validated against the diffusers reference; AdaLN precompute dro…☆28Oct 8, 2026Updated last week
- Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE☆151Updated this week
- Convert and Run Exl3 format LLM quant on Apple Silicon.☆58Aug 24, 2026Updated last month
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- A front door to community tools that extend the DeepSeek Harness (dsh): web access, vision, and more. Unofficial community project.☆42Sep 28, 2026Updated 2 weeks ago
- Local AI registry: one validated recipe per machine, with the evidence attached☆254Updated this week
- Sushi engine runs very high quality quant model in Apple Silicon, using hybrid affine/exl3 with special expert tuning techniques.☆270Updated this week
- Prompt for generating 3D models in mechanical deployable style.☆98Aug 26, 2026Updated last month
- A GEPA proposer with less overfitting and helpful parameters.☆60Oct 6, 2026Updated last week
- Real browser automation with local GLiNER2 inference and open weights. Work in progress. Contributions welcome.☆80Sep 18, 2026Updated 3 weeks ago
- Metal Cuda Direct Memory Access☆196Updated this week