schema_version: 1
model:
  id: smollm2-1-7b-instruct
  display_name: SmolLM2-1.7B-Instruct
  architecture: LlamaForCausalLM
  model_type: llama
  parameter_count: 1711376384
  context_length: 8192
  tokenizer_type: GPT2Tokenizer
  tasks:
  - text-generation
  chat_template: true
  multimodal: false
  custom_code: false
  safetensors: true
upstream:
  repo: HuggingFaceTB/SmolLM2-1.7B-Instruct
  revision: 31b70e2e869a7173562077fd711b654946d38674
  license:
    identifier: apache-2.0
    redistribution: allowed
    reason: Upstream declares a recognized license that permits redistribution; retain
      its terms and attribution.
  gated: false
  private: false
  source_url: https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct
packages:
- id: gguf-q4-k-m
  format: gguf
  precision: Q4_K_M
  filename: SmolLM2-1.7B-Instruct-Q4_K_M.gguf
  sha256: 5ac93b9ab47d7b3069282f1cef65e1534e68b2c97d1ec129288bc792fa33ec5c
  size_bytes: 1055609344
  bits_per_weight: 4.83
  runtime:
    provider: llama.cpp
    tested_revision: de699957b92f490efebad149665b0dccf127eaff
  hardware:
    estimated_ram_gb: 1.27
    estimated_vram_gb: 1.16
    recommended_ram_gb: 2.43
    note: Estimate; runtime use varies with context length and configuration.
  validation:
    integrity: passed
    metadata: passed
    load: passed
    inference: passed
    tokenizer: passed
    tested_at: '2026-08-22T16:19:42.516982Z'
    details:
      version: '3'
      tensor_count: '218'
      metadata_count: '30'
- id: gguf-q5-k-m
  format: gguf
  precision: Q5_K_M
  filename: SmolLM2-1.7B-Instruct-Q5_K_M.gguf
  sha256: a2fdd913de171cea397f3c876e9b23af9a899491e0dd32958affa2ec44c5d99c
  size_bytes: 1225478656
  bits_per_weight: 5.67
  runtime:
    provider: llama.cpp
    tested_revision: de699957b92f490efebad149665b0dccf127eaff
  hardware:
    estimated_ram_gb: 1.47
    estimated_vram_gb: 1.35
    recommended_ram_gb: 2.65
    note: Estimate; runtime use varies with context length and configuration.
  validation:
    integrity: passed
    metadata: passed
    load: passed
    inference: passed
    tokenizer: passed
    tested_at: '2026-08-22T16:19:49.471593Z'
    details:
      version: '3'
      tensor_count: '218'
      metadata_count: '30'
- id: gguf-q8-0
  format: gguf
  precision: Q8_0
  filename: SmolLM2-1.7B-Instruct-Q8_0.gguf
  sha256: af66f269a1a77bd0b0df4f5a123b96582f1dac700b7846e0880b3eb54fa4f563
  size_bytes: 1820414464
  bits_per_weight: 8.5
  runtime:
    provider: llama.cpp
    tested_revision: de699957b92f490efebad149665b0dccf127eaff
  hardware:
    estimated_ram_gb: 2.18
    estimated_vram_gb: 2.0
    recommended_ram_gb: 3.46
    note: Estimate; runtime use varies with context length and configuration.
  validation:
    integrity: passed
    metadata: passed
    load: passed
    inference: passed
    tokenizer: passed
    tested_at: '2026-08-22T16:19:57.607061Z'
    details:
      version: '3'
      tensor_count: '218'
      metadata_count: '30'
generated_at: '2026-08-22T16:19:59.672602Z'