diff --git a/stacks/voxtral/.env.example b/stacks/voxtral/.env.example
index bef2e6f..7850f9f 100644
--- a/stacks/voxtral/.env.example
+++ b/stacks/voxtral/.env.example
@@ -30,6 +30,14 @@ VOXTRAL_GPU_DEVICES=1
 # alongside other GPU workloads on the same device.
 VOXTRAL_GPU_UTIL=0.85
 
+# ── HuggingFace auth ─────────────────────────────────────────────────
+# HF_TOKEN — required to dodge 429 rate limits on Voxtral download.
+# HF aggressively throttles unauthenticated IPs that pull large repos.
+# Generate one at https://huggingface.co/settings/tokens (a read-only
+# token is sufficient). Without this, the first model download fails
+# mid-stream and vLLM aborts engine init.
+VOXTRAL_HF_TOKEN=
+
 # ── persistent storage on the host ───────────────────────────────────
 # HF cache — first start pulls the Voxtral checkpoint (~8 GB) into
 # this dir. Persistent across container recreates.
diff --git a/stacks/voxtral/compose.yaml b/stacks/voxtral/compose.yaml
index 591a1c0..3d23024 100644
--- a/stacks/voxtral/compose.yaml
+++ b/stacks/voxtral/compose.yaml
@@ -28,6 +28,10 @@ services:
     environment:
       - NVIDIA_VISIBLE_DEVICES=${VOXTRAL_GPU_DEVICES:-1}
       - HF_HOME=/root/.cache/huggingface
+      # HF_TOKEN required to dodge 429 rate limits on the model
+      # download (HF aggressively throttles unauthenticated IPs that
+      # pull large repos repeatedly). Set in .env — see .env.example.
+      - HF_TOKEN=${VOXTRAL_HF_TOKEN}
       # vLLM serving args — see https://docs.vllm.ai for full list.
       # We override the default model via cmd args below.
     volumes:
@@ -43,6 +47,13 @@ services:
       - "--port=8000"
       - "--dtype=bfloat16"
       - "--gpu-memory-utilization=${VOXTRAL_GPU_UTIL:-0.85}"
+      # Voxtral uses the native Mistral model format (params.json,
+      # tekken.json tokenizer, consolidated.safetensors) — NOT HF
+      # transformers format. vLLM rejects it with "ensure presence
+      # of params.json" unless these three flags are set.
+      - "--load-format=mistral"
+      - "--tokenizer-mode=mistral"
+      - "--config-format=mistral"
     healthcheck:
       # vLLM-Omni exposes /health for liveness + /v1/models for readiness.
       # /health 200 means the server's listening; /v1/models 200 means