schema: onefrontier.launch-card/v1
hf:
  repo: Qwen/Qwen3-8B
  revision: b968826d9c46dd6066d109eabc6255188de91218
  license: apache-2.0
  gated: false
  params_b: 8.19
  modality:
  - text-generation
  weight_gib: 15.3
  last_modified: '2025-07-26T03:49:13.000Z'
  downloads: 7851416
checkpoints:
- name: root
  format: bf16
  subdir: null
  source_repo: null
  resident_gib: 15.3
  host_gib: null
  gated: false
  notes: 5 weight file(s)
envs:
- engine: vllm
  checkpoint: root
  engine_version: null
  image: vllm/vllm-openai-cpu:latest-x86_64
  argv:
  - vllm
  - serve
  - Qwen/Qwen3-8B
  - --tensor-parallel-size
  - '1'
  - --max-num-batched-tokens
  - '16384'
  - --gpu-memory-utilization
  - '0.8'
  - --enable-auto-tool-choice
  - --tool-call-parser
  - hermes
  - --reasoning-parser
  - qwen3
  command: "vllm serve Qwen/Qwen3-8B \\\n  --tensor-parallel-size 1 \\\n  --max-num-batched-tokens\
    \ 16384 \\\n  --gpu-memory-utilization 0.8 \\\n  --enable-auto-tool-choice \\\n\
    \  --tool-call-parser hermes \\\n  --reasoning-parser qwen3"
  env: {}
  validated_hardware:
  - xeon6
  notes: null
  source:
    kind: vllm-recipes
    url: https://recipes.vllm.ai/Qwen/Qwen3-8B.json
    fetched_at: null
hardware:
  gpu_models: []
  gpu_arch: []
  min_gpus: 1
  tp_rule: widest published TP is 1
  min_vram_per_gpu_gib: null
  min_total_vram_gib: null
  min_disk_gib: 68
  min_host_ram_gib: null
  interconnect: null
  cuda_min: null
  driver_min: null
  context_tokens: null
performance: https://onefrontier.ai/Qwen/Qwen3-8B/performance
evidence:
- kind: hf-api
  url: https://huggingface.co/api/models/Qwen/Qwen3-8B
  fetched_at: null
- kind: vllm-recipes
  url: https://recipes.vllm.ai/Qwen/Qwen3-8B.json
  fetched_at: null
gaps:
- field: envs.sglang
  why: no SGLang cookbook page matched this repo
- field: hardware.validated
  why: 'the only verified targets are non-GPU: xeon6 — no GPU family was verified
    for this repo'
captured_at: '2026-10-31T17:28:13Z'
captured_by: hf-api + vllm-recipes + sglang-cookbook