StackMap
Subscribe
Explore / Strata
Niko1221

Strata

Hybrid GPU/CPU MoE engine that runs Qwen3.8-Flash-Next and DeepSeek V4.1 on consumer cards: hot experts cached in VRAM, rest computed in RAM, MTP drafting, local OpenAI/Anthropic API.

40,551 4,431 C++ MITupdated yesterday
localcoding
View on GitHubDispute this mapping →
Curator's take

Reach for it when you own a 12-24 GB GPU (NVIDIA, AMD, Apple Silicon) and want a frontier-class MoE behind Claude Code, Codex or OpenCode with no cloud — one installer, `strata connect` wires the tools. It is a purpose-built engine for a handful of model families, not a general runner: for arbitrary GGUFs or multi-user serving use Ollama/vLLM, and on low RAM or small disks the DeepSeek packs (200+ GB) will not fit.

Mapped by ShipWithAI editors · links verified

Continue your stack

What teams reach for next — and why each earns a place beside Strata. Ranked by curator confidence.

pairs wellalternativealternativealternativealternativeLynkrFreeTokencolibrimagnitudeuzuStrata
pairs wellalternativebuilt withpick a node for the why · open it from the panel
Weekly digest
README.md2 min read

Strata

Run powerful AI on your own computer.

Chat, code and work with images, locally.

Models · Install · Hardware · Tools · Help · Support

Download Strata MIT license Sponsor Strata on GitHub Sponsors Support Strata on Buy Me a Coffee

English · 简体中文 · 日本語 · Deutsch · Français · Español · Português · Polski

Free, open source, and yours to run. Use Strata on your desktop or with your favorite coding tools. No account needed.

Models

We recommend ISTA-DASLab first, then Unsloth and other providers, where a compatible model fits.

 Qwen3.8-Flash-Next
Provider Choices
ISTA-DASLab · recommended Q2_0, IQ2_XS, IQ3_XXS, IQ3_S. Coder: IQ1_M for coding.
Unsloth UD-IQ4_XS, UD-Q4_K_XL, UD-Q5_K_XL, UD-Q6_K_XL, Q8_0
Gyro · agentionai Gyro-S, Gyro-M. Lower memory use but slower.
Other options Swift 1.5, NVFP4, OrcaRouter

Compare sizes, memory needs and compatibility.

 Qwen3.6-35B-A3B

Unsloth: UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. These are the currently documented packs for this model.

Model guide and compatibility.

 DeepSeekV4.1-Flash-1017

In the desktop app and the Terminal. What does not fit in memory is read from your SSD, so it needs a lot of free disk space.

Set (ISTA-DAS) Download Free disk needed
1.75 bpw 239 GB about 245 GB
2.00 bpw 257 GB about 265 GB
2.25 bpw 274 GB about 280 GB
ISTA-DAS Coder (half of the experts removed) 191 GB about 197 GB

Runs on NVIDIA RTX 30, 40 and 50 series (Windows and Linux), AMD Radeon AI PRO R9700 (Linux), AMD Ryzen AI Max — Strix Halo (Windows), and Apple Silicon Macs with 64 GB or more, text only (Mac). Setup downloads the files and the DeepSeek engine, then starts the model.

strata launch --family deepseek41 --model ist-das-2.00bpw --plan

Measured with the 2.00 bpw set on Strata 0.2.5 (Strix Halo: 0.2.7). Output is the speed of the answer, prompt is how fast Strata reads your input.

Hardware Output Prompt
RTX 5070 12 GB, 64 GB RAM 4 to 6 tokens/s about 110 t