# Model Blob SHA-256 Hashes — Day 1 Lab
# Recorded at M3 build time (2026-07-07) via `ollama show` on ollama/ollama:0.9.3
#
# These are content-addressed Ollama model blob hashes (ADR-6).
# If the SHA-256 matches after pulling, you have exactly the same model weights.
#
# Verify after pulling:
#   docker compose exec ollama ollama show nomic-embed-text:v1.5
#   (look for the manifest at ~/.ollama/models/manifests/registry.ollama.ai/library/...)
#
# Air-gapped verification: check that blob files exist in the volume:
#   docker compose exec ollama ls /root/.ollama/models/blobs/sha256-<first-64-chars>

# ── nomic-embed-text:v1.5 ─────────────────────────────────────────────────────
# Architecture: nomic-bert | Parameters: 136.73M | Quantization: F16
# Context length: 2048 | Embedding length: 768 | License: Apache 2.0
#
# Main GGUF blob (274 MB):
NOMIC_EMBED_TEXT_V1_5_BLOB_SHA256=970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6
#
# Config/manifest SHA-256:
NOMIC_EMBED_TEXT_V1_5_CONFIG_SHA256=31df23ea7daa448f9ccdbbcecce6c14689c8552222b80defd3830707c0139d4f

# ── qwen2.5:1.5b ─────────────────────────────────────────────────────────────
# Architecture: qwen2 | Parameters: 1.5B | Quantization: Q4_K_M
# Context length: 32768 | Embedding length: 1536 | License: Apache 2.0
# Capabilities: completion + tools (tool-calling capable even at 1.5B)
#
# Main GGUF blob (986 MB, Q4_K_M quantized):
QWEN2_5_1_5B_BLOB_SHA256=183715c435899236895da3869489cc30ac241476b4971a20285b1a462818a5b4
#
# Config/manifest SHA-256:
QWEN2_5_1_5B_CONFIG_SHA256=377ac4d7aeefd5b870c9fccff9a6d4df36901d99fe3277c2f755bc401601ba1c

# ── Total download size ───────────────────────────────────────────────────────
# nomic-embed-text:v1.5:  274 MB
# qwen2.5:1.5b:           986 MB
# Total (approximate):  1,260 MB (~1.2 GB)
#
# Ollama model registry: registry.ollama.ai (not Docker Hub)
# These hashes are for the Ollama model format (GGUF + metadata layers),
# not the Ollama Docker image digest.
