The models the EU operator will serve at mainnet · famous open-weight models that fit the phase-0 cluster
| # | Model | Pipeline | Library | License | Status |
|---|---|---|---|---|---|
| 1 | stabilityai/stable-diffusion-xl-base-1.0 | text-to-image | diffusers | openrail++ | queued |
| 2 | CompVis/stable-diffusion-v1-4 | text-to-image | diffusers | creativeml-openrail-m | queued |
| 3 | meta-llama/Meta-Llama-3-8B | text-generation | transformers | llama3 | queued |
| 4 | hexgrad/Kokoro-82M | text-to-speech | — | apache-2.0 | queued |
| 5 | meta-llama/Llama-3.1-8B-Instruct | text-generation | transformers | llama3.1 | queued |
| 6 | openai/whisper-large-v3 | automatic-speech-recognition | transformers | apache-2.0 | queued |
| 7 | black-forest-labs/FLUX.1-schnell | text-to-image | diffusers | apache-2.0 | queued |
| 8 | sentence-transformers/all-MiniLM-L6-v2 | sentence-similarity | sentence-transformers | apache-2.0 | queued |
| 9 | meta-llama/Llama-2-7b-chat-hf | text-generation | transformers | llama2 | queued |
| 10 | Tongyi-MAI/Z-Image-Turbo | text-to-image | diffusers | apache-2.0 | queued |
| 11 | meta-llama/Meta-Llama-3-8B-Instruct | text-generation | transformers | llama3 | queued |
| 12 | meta-llama/Llama-2-7b | text-generation | — | llama2 | queued |
| 13 | mistralai/Mistral-7B-v0.1 | text-generation | transformers | apache-2.0 | queued |
| 14 | lllyasviel/ControlNet-v1-1 | — | — | openrail | queued |
| 15 | WarriorMama777/OrangeMixs | text-to-image | diffusers | creativeml-openrail-m | queued |
| 16 | lllyasviel/ControlNet | — | — | openrail | queued |
| 17 | deepseek-ai/Janus-Pro-7B | any-to-any | transformers | mit | queued |
| 18 | microsoft/phi-2 | text-generation | transformers | mit | queued |
| 19 | google/gemma-7b | text-generation | transformers | gemma | queued |
| 20 | openai-community/gpt2 | text-generation | transformers | mit | queued |
| 21 | deepseek-ai/DeepSeek-OCR | image-text-to-text | transformers | mit | queued |
| 22 | prompthero/openjourney | text-to-image | diffusers | creativeml-openrail-m | queued |
| 23 | mistralai/Mistral-7B-Instruct-v0.2 | text-generation | transformers | apache-2.0 | queued |
Rust 1.80+ · macOS · Linux · Windows
# Requires Rust 1.80+. $ cargo install --git https://github.com/Concordfaces/concord concord-cli $ concord --version
# Linux / macOS — shasum-verified install $ curl -fsSL https://concordfaces.org/install.sh | sh # Windows (PowerShell) PS> iwr https://concordfaces.org/install.ps1 -useb | iex # From source $ git clone https://github.com/Concordfaces/concord $ cd concord && cargo build --release $ ./target/release/concord --help
Verified ed25519 signature · content-addressed blake3 chunks
# Pull a model from the EU operator. $ concord pull sentence-transformers/all-MiniLM-L6-v2 # Verify the manifest signature + every chunk digest. $ concord verify sentence-transformers/all-MiniLM-L6-v2 # Pull a specific version (omit for latest signed). $ concord pull BAAI/bge-small-en-v1.5:v1 # Show local cache. $ concord list --cached
api.eu.concordfaces.org for the EU operator. Override with --endpoint https://api.<op>.concordfaces.org or set CONCORD_ENDPOINT. Cache lives at ~/.cache/concord (override with CONCORD_CACHE or $XDG_CACHE_HOME/concord).
Drop-in compatibility · zero code changes for most pipelines
api.<op>.concordfaces.org/hf.
HF_ENDPOINT and any tool that respects
it routes through Concordfaces — no client patching.
~/.cache/huggingface/hub,
so transformers, sentence-transformers, diffusers, and vLLM pick them up unchanged.
$ pip install huggingface_hub $ export HF_ENDPOINT=https://api.eu.concordfaces.org/hf $ huggingface-cli download \ sentence-transformers/all-MiniLM-L6-v2 # Files land in the standard HF cache layout. # ~/.cache/huggingface/hub/models--<org>--<name>/
# Either set the env var once … $ export HF_ENDPOINT=https://api.eu.concordfaces.org/hf # … or pass `endpoint=` explicitly per call. >>> from huggingface_hub import snapshot_download >>> snapshot_download( ... "BAAI/bge-small-en-v1.5", ... endpoint="https://api.eu.concordfaces.org/hf", ... )
concord over huggingface-cli?
The native client streams signed manifest envelopes and verifies every blake3 chunk against
the operator's ed25519 key on the wire — the HF shim is byte-for-byte compatible but the
signature check happens server-side. Use concord verify after an HF-style pull
if you need end-to-end proof.
concord token mint) and are logged per manifest by the
serving operator, regardless of which client you use.