Llama-3.1-8B-Instruct TIC

Bit-exact lossless .tic compression of meta-llama/Llama-3.1-8B-Instruct.

Same weights. No quantization.

What is TIC?

Precision BF16
Raw weights 16.06 GB
.tic weights 11.44 GB (28.8% savings)

Benchmarks

Benchmarks for methodology and results.

Run

# Install
curl -fsSL https://isiro.ai/install.sh | sh

# Download .tic bundle
pip install -U huggingface_hub
hf download isiroai/Llama-3.1-8B-Instruct-TIC --local-dir Llama-3.1-8B-Instruct-TIC

# Serve (vLLM supported today)
isiro serve Llama-3.1-8B-Instruct-TIC --target vllm

Install options · Serve docs · Compile your own

Verify

Bit-exact checks. Hash manifest: model.tic.manifest.json.

# Confirm .tic integrity via the hash manifest
isiro verify Llama-3.1-8B-Instruct-TIC

# Optional: confirm .tic weights match the raw weights (requires compiler)
hf download meta-llama/Llama-3.1-8B-Instruct --local-dir Llama-3.1-8B-Instruct
isiro verify Llama-3.1-8B-Instruct-TIC -r Llama-3.1-8B-Instruct

License

Weights: same license as meta-llama/Llama-3.1-8B-Instruct (Llama 3.1 Community License). See also USE_POLICY.md.

.tic, ISIRO Runtime, and Compiler: ISIRO EULA.

Downloads last month
2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support