Skip to content
memoctetDownload
Language English

smollm2-1.7b-instruct-q4_k_m

This seed file names one model file by its SHA-256. The player downloads it, checks every byte and runs it on your CPU, or refuses.

  • Passed start-up
  • Same on Linux and Windows
  • Same on AMD and Intel, same OS

Use this seed

Download the playerHave the player? Run it

Needs

  • RAM: the player refuses below 1006.7 MiB
  • Peak memory: not measured for this seed. The player compares your RAM with the file size, not with the memory it will use; on the 2 seeds we measured, the largest process peaked 49% and 77% above the file size (Linux, )
  • Free disk ≥ 1.03 GiB
  • x86-64 processor with AVX2, FMA and F16C
  • Linux (glibc 2.35 or newer) or Windows 11 (builds 26100 and 26200 measured)

The player checks RAM, free disk and the processor before downloading, and stops if any of them falls short; a value it cannot read does not stop it.

Downloads 1006.7 MiB from Hugging Face.

Seed file · 513 bytes · already in the player's archive, catalogue folder

Seed smollm2-17b · 513 bytes

Model and file by HuggingFaceTB (HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF)

Apache-2.0 · No extra terms (keep the licence notice) · label and model card read; licence file not opened · as declared, read · not legal advice

Linux vs Windows comparison: same tokens on 3 test questions, 2 machines, .

Run it

From the unpacked player folder. --maison is the folder for this model and your conversations.

Linux · bash
# germer: download the model file and check every byte./memown germer catalogue/smollm2-17b.graine.json --maison ~/ia/smollm2-17b

Expected: a line starting with VERDICT : VERT (VERT: all four checks passed, including the byte-for-byte check)

Windows 11 · PowerShell
# germer: download the model file and check every byte.\memown.exe germer catalogue\smollm2-17b.graine.json --maison "$env:USERPROFILE\ia\smollm2-17b"

Expected: a line starting with VERDICT : VERT (VERT: all four checks passed, including the byte-for-byte check)

Compare your answer with ours

Ask it first, right after germer, in a new --maison folder. Type the question exactly, in French: the published fingerprint is for these exact bytes.

Expected: 10 tokens, seen on 5 machines (Linux and Windows 11), to , 0 differences · fingerprint 15a1045938eb85fab57e2f7ad4e02b9221c9b24304b0c25740fc71dcdfdc3814 Click once to select the whole value.

Linux · bash
# parler: ask a question./memown parler --maison ~/ia/smollm2-17b --dire "Quelle est la capitale de la France ?"grep -c '"ids_sha256":"15a1045938eb85fab57e2f7ad4e02b9221c9b24304b0c25740fc71dcdfdc3814"' ~/ia/smollm2-17b/vies/vie/journal.json

Expected: 1

Windows 11 · PowerShell
# parler: ask a question.\memown.exe parler --maison "$env:USERPROFILE\ia\smollm2-17b" --dire "Quelle est la capitale de la France ?"Select-String -Quiet -SimpleMatch -Path "$env:USERPROFILE\ia\smollm2-17b\vies\vie\journal.json" -Pattern '"ids_sha256":"15a1045938eb85fab57e2f7ad4e02b9221c9b24304b0c25740fc71dcdfdc3814"'

Expected: True

1 or True: your tokens are the same as ours. 0 or False: they differ. Tell us either way.

To ask your own question, change the text after --dire. Keep the test question to compare with ours.

What this seed names

Model file
smollm2-1.7b-instruct-q4_k_m.gguf
Size
1,055,609,536 bytes (1006.7 MiB)
SHA-256
decd2598bc2c8ed08c19adc3c8fdd461ee19ed5708679d1c54ef54a5a30d4f33
Hosted at
Hugging Face gave the same SHA-256 for this file (checked ) · If that file changes, the player refuses it.
Licence
Apache-2.0 · No extra terms
Seed file
smollm2-17b.graine.json · 513 bytes · e48c1fe86995aafb8772d11b4c08df5ff5bb366bce5c0dd958e02ada7fe59d17

What we measured

  • Start-up: passed on when the seed was made (Linux, glibc 2.35).
  • Linux vs Windows: same tokens · 3 test questions · 2 machines · · data (JSON)
  • AMD vs Intel, same OS: same tokens · 3 test questions · 2 machines ·
  • 12 expected answers · up to 5 machines · 0 differences
  • 36.8–55.2 tokens/s · 3 rented AMD EPYC servers shared with other work · 8 threads · short answers in a new conversation · player 1.2, same engines as 1.3.1 · . Your speed: not measured.

Not measured for this seed

  • Peak memory

Not measured for any seed: see Measurements.

12 expected answers
QuestionExpectedMeasured
Quelle est la capitale de la France ? (“What is the capital of France?”)10 tokens · SHA-256 of the token IDs 15a10459…c38145 machines
Continue la suite : 2, 4, 8, 16, (“Continue the sequence: 2, 4, 8, 16,”)30 tokens · SHA-256 of the token IDs f1e94c58…2ab5f3 machines
What is the capital of Italy?12 tokens · SHA-256 of the token IDs d8af47ce…3d8f44 machines
Continue la suite : 2, 4, 8, 16, (“Continue the sequence: 2, 4, 8, 16,”)32 tokens · SHA-256 of the token IDs 2e718ac3…e09c14 machines
Explique en deux phrases pourquoi le ciel est bleu. (“Explain in two sentences why the sky is blue.”)56 tokens · SHA-256 of the token IDs 9d7fcf80…cf93d3 machines
Recopie exactement : le chat dort sur le tapis rouge et la pluie tombe doucement. (“Copy exactly: the cat sleeps on the red rug and the rain falls gently.”)22 tokens · SHA-256 of the token IDs d19ec7a5…7af083 machines
Donne trois nombres premiers entre 10 et 30. (“Give three prime numbers between 10 and 30.”)32 tokens · SHA-256 of the token IDs ed9a63cf…177c43 machines
Traduis en anglais : la mer est calme ce soir. (“Translate into English: the sea is calm tonight.”)8 tokens · SHA-256 of the token IDs d8fc5c1f…a51963 machines
Quel est le plus grand océan du monde ? (“What is the largest ocean in the world?”)19 tokens · SHA-256 of the token IDs fe40cfea…f49173 machines
Écris une phrase de politesse pour finir un e-mail. (“Write a polite sentence to end an email.”)35 tokens · SHA-256 of the token IDs 82b268ab…387663 machines
Résume en une phrase ce que fait un four à pain. (“Sum up in one sentence what a bread oven does.”)10 tokens · SHA-256 of the token IDs 2bf7af14…1d1d03 machines
Continue la suite : 3, 6, 12, 24, (“Continue the sequence: 3, 6, 12, 24,”)30 tokens · SHA-256 of the token IDs ad1905d4…be9423 machines
The seed file (JSON, 513 bytes)
{"matiere":{"nom":"smollm2-1.7b-instruct-q4_k_m.gguf","octets":1055609536,"sha256":"decd2598bc2c8ed08c19adc3c8fdd461ee19ed5708679d1c54ef54a5a30d4f33","substrat":["hf:HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF/smollm2-1.7b-instruct-q4_k_m.gguf"]},"nom":"smollm2-17b","notes":"licence declaree par l hebergeur : apache-2.0. les poids ne sont pas ici : ils sont NOMMES.","recette":{"classe":"x86-64-fils8","empreinte":"869bef8788166262e4a72fe04f0809756f561a2bae03a52a95e3fb7f294b8226"},"scellee_le":"2026-08-17","v":1}
Licence as we read it, in French

Aucun seuil, aucune obligation de nommage.

Ce qui suit la redistribution est ce qu'Apache 2.0 exige : joindre une copie de la licence, conserver les mentions de droit d'auteur, de brevet et d'attribution, et signaler les fichiers modifiés.

étiquette et carte du dépôt amont lues (étiquette croisée README brut + API) ; le fichier de licence lui-même n'a pas été ouvert

huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct

Full record, in French