schema_version: 1
model:
  id: smollm2-135m-instruct
  display_name: SmolLM2-135M-Instruct
  architecture: LlamaForCausalLM
  model_type: llama
  parameter_count: 134515008
  context_length: 8192
  tokenizer_type: GPT2Tokenizer
  tasks:
  - text-generation
  chat_template: true
  multimodal: false
  custom_code: false
  safetensors: true
upstream:
  repo: HuggingFaceTB/SmolLM2-135M-Instruct
  revision: 12fd25f77366fa6b3b4b768ec3050bf629380bac
  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/SmolLM2-135M-Instruct
packages:
- id: gguf-q4-k-m
  format: gguf
  precision: Q4_K_M
  filename: SmolLM2-135M-Instruct-Q4_K_M.gguf
  sha256: dd18a11b8634d1684448986b8c166f75319f52082d759654aaa8fe5bd2f057e3
  size_bytes: 105453984
  bits_per_weight: 4.83
  runtime:
    provider: llama.cpp
    tested_revision: de699957b92f490efebad149665b0dccf127eaff
  hardware:
    estimated_ram_gb: 0.13
    estimated_vram_gb: 0.12
    recommended_ram_gb: 1.14
    note: Estimate; runtime use varies with context length and configuration.
  validation:
    integrity: passed
    metadata: passed
    load: passed
    inference: passed
    tokenizer: passed
    tested_at: '2026-08-20T20:24:16.685253Z'
    details:
      version: '3'
      tensor_count: '272'
      metadata_count: '30'
- id: gguf-q5-k-m
  format: gguf
  precision: Q5_K_M
  filename: SmolLM2-135M-Instruct-Q5_K_M.gguf
  sha256: 00680963c363ba10593daf7568dd6e1ee4c4771a608fe1b4e43f86b564d9b823
  size_bytes: 112103328
  bits_per_weight: 5.67
  runtime:
    provider: llama.cpp
    tested_revision: de699957b92f490efebad149665b0dccf127eaff
  hardware:
    estimated_ram_gb: 0.13
    estimated_vram_gb: 0.12
    recommended_ram_gb: 1.15
    note: Estimate; runtime use varies with context length and configuration.
  validation:
    integrity: passed
    metadata: passed
    load: passed
    inference: passed
    tokenizer: passed
    tested_at: '2026-08-20T20:24:18.938307Z'
    details:
      version: '3'
      tensor_count: '272'
      metadata_count: '30'
- id: gguf-q8-0
  format: gguf
  precision: Q8_0
  filename: SmolLM2-135M-Instruct-Q8_0.gguf
  sha256: ee785d9b4836ddb57207ae6daa630206a756c99fc52e19696f1e2ea2e8a41b99
  size_bytes: 144810912
  bits_per_weight: 8.5
  runtime:
    provider: llama.cpp
    tested_revision: de699957b92f490efebad149665b0dccf127eaff
  hardware:
    estimated_ram_gb: 0.17
    estimated_vram_gb: 0.16
    recommended_ram_gb: 1.2
    note: Estimate; runtime use varies with context length and configuration.
  validation:
    integrity: passed
    metadata: passed
    load: passed
    inference: passed
    tokenizer: passed
    tested_at: '2026-08-20T20:24:21.225025Z'
    details:
      version: '3'
      tensor_count: '272'
      metadata_count: '30'
generated_at: '2026-08-20T20:32:10.805207Z'