lablup / mlxcel

brew tap lablup/tap
brew install mlxcel

# Interactive chat.
mlxcel run Qwen3.5-0.8B-4bit

# One-shot generation, then exit.
mlxcel run Qwen3.5-0.8B-4bit -p "Hello, world!" -n 100

# With no model argument, use mlx-community/gemma-4-e2b-it-4bit.
mlxcel run

mlxcel generate -m Qwen3.5-0.8B-4bit -p "Hello, world!" -n 100

# Read-only memory estimate before loading.
mlxcel inspect -m Qwen3.5-0.8B-4bit --max-tokens 32768

# Emit the same estimate as machine-readable bytes for recipe builders or schedulers.
mlxcel inspect --json -m Qwen3.5-0.8B-4bit --max-tokens 32768 | python3 -m json.tool

# Abort before generation if the estimated model and KV cache do not fit.
mlxcel generate -m Qwen3.5-0.8B-4bit -p "Hello" -n 32768 --estimate-memory

mlxcel-server -m Qwen3.5-0.8B-4bit --port 8080

curl http://localhost:8080/v1/chat/completions \
-H 'Content-Type: application/json' \
-d '{"model":"Qwen3.5-0.8B-4bit","messages":[{"role":"user","content":"Hello"}]}'

# API keys from a list or file; both sources are combined.
mlxcel-server -m Qwen3.5-0.8B-4bit --api-key alice-key,bob-key
mlxcel-server -m Qwen3.5-0.8B-4bit --api-key-file /etc/mlxcel/api-keys

# Restrict browser CORS, or serve HTTPS.
mlxcel-server -m Qwen3.5-0.8B-4bit \
--allowed-origins https://app.example.com,https://admin.example.com
mlxcel-server -m Qwen3.5-0.8B-4bit \
--ssl-cert-file cert.pem --ssl-key-file key.pem

# Serve below a path prefix or on a Unix domain socket.
mlxcel-server -m Qwen3.5-0.8B-4bit --api-prefix /llama
mlxcel-server -m Qwen3.5-0.8B-4bit --host /run/mlxcel.sock

# Router mode: discover direct checkpoint subdirectories under /srv/models,
# use the global store as another source, and keep at most four models loaded.
mlxcel-server --models-dir /srv/models \
--model-store-root /var/lib/mlxcel/models --models-max 4

# Embed two texts and print vectors plus cosine similarity.
mlxcel embed -m sentence-transformers/all-MiniLM-L6-v2 \
-p "The weather is lovely" -p "It is sunny"

# Rank documents against one query.
mlxcel rerank -m BAAI/bge-reranker-v2-m3 \
-q "what is panda?" -d "hi" -d "The giant panda is a bear species."

# Serve embeddings alone, or a reranker beside a chat model.
mlxcel-server -m sentence-transformers/all-MiniLM-L6-v2 --port 8080
mlxcel-server -m Qwen3.5-0.8B-4bit \
--reranker-model mlx-community/Qwen3-Reranker-0.6B-4bit --port 8080

mlxcel-server -m models/whisper-base --port 8080

curl http://localhost:8080/v1/audio/transcriptions \
-F file=@recording.wav -F model=whisper-base

mlxcel list                  # name, size, and modified time
mlxcel list --sort size      # largest first
mlxcel list --json           # stable machine-readable array
mlxcel list -q               # repository ids only
mlxcel list -v               # include absolute paths

mlxcel rm mlx-community/Qwen3.5-0.8B-4bit
mlxcel rm mlx-community/Qwen3.5-0.8B-4bit --yes

# Object detection with an RT-DETRv2 checkpoint.
mlxcel detect -m models/rt-detr-v2 -i image.jpg --format json

# Inspect the hardware-specific kernel tuning matrix without profiling it.
mlxcel tune --dry-run

# Split the GLM-4.7-Flash MTP block out of the raw checkpoint into a 4-bit
# drafter, then pair it with a glm4_moe_lite target.
mlxcel split-mtp -m models/glm-4.7-flash-bf16 -o models/glm-4.7-flash-mtp-4bit --q-bits 4
mlxcel generate -m models/glm-4.7-flash-4bit --draft-model models/glm-4.7-flash-mtp-4bit -p "Hello"

xcodebuild -downloadComponent MetalToolchain
git clone https://github.com/lablup/mlxcel.git
cd mlxcel
cargo build --release --features metal,accelerate

cargo build --release --features cuda

cargo build --release --features rocm