DeepSeek-R1-Distill-Qwen-7B-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 itNeeds
- RAM: the player refuses below 4.36 GiB
- 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 ≥ 4.58 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 4.36 GiB from Hugging Face.
Seed file · 519 bytes · already in the player's archive,catalogue folderSeed r1-qwen-7b · 519 bytes
Model by deepseek-ai · file converted by bartowski (bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF)
MIT · 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.
# germer: download the model file and check every byte./memown germer catalogue/r1-qwen-7b.graine.json --maison ~/ia/r1-qwen-7b Expected: a line starting with VERDICT : VERT (VERT: all four checks passed, including the byte-for-byte check)
# germer: download the model file and check every byte.\memown.exe germer catalogue\r1-qwen-7b.graine.json --maison "$env:USERPROFILE\ia\r1-qwen-7b" Expected: a line starting with VERDICT : VERT (VERT: all four checks passed, including the byte-for-byte check)
Compare your answer with ours
Ask it first, right after germer, in a new --maison folder. Type the question exactly, in French: the published fingerprint is for these exact bytes.
Expected: 120 tokens, seen on 5 machines (Linux and Windows 11), to , 0 differences · fingerprint e45482f030e883a7559e607e8d2bea95084e8e79fd69907b68d1296abdf13d41 Click once to select the whole value.
# parler: ask a question./memown parler --maison ~/ia/r1-qwen-7b --dire "Quelle est la capitale de la France ?"grep -c '"ids_sha256":"e45482f030e883a7559e607e8d2bea95084e8e79fd69907b68d1296abdf13d41"' ~/ia/r1-qwen-7b/vies/vie/journal.json Expected: 1
# parler: ask a question.\memown.exe parler --maison "$env:USERPROFILE\ia\r1-qwen-7b" --dire "Quelle est la capitale de la France ?"Select-String -Quiet -SimpleMatch -Path "$env:USERPROFILE\ia\r1-qwen-7b\vies\vie\journal.json" -Pattern '"ids_sha256":"e45482f030e883a7559e607e8d2bea95084e8e79fd69907b68d1296abdf13d41"'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
DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf- Size
- 4,683,073,504 bytes (4.36 GiB)
- SHA-256
731ece8d06dc7eda6f6572997feb9ee1258db0784827e642909d9b565641937b- Hosted at
- Hugging Face gave the same SHA-256 for this file (checked ) · If that file changes, the player refuses it.
- Licence
- MIT · No extra terms
- Seed file
r1-qwen-7b.graine.json· 519 bytes ·a1e0c2431e6d04304d3c9d70b9339919a07f888072af48c8f3803e53c6b85830
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
- 9.9–19.8 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
| Question | Expected | Measured |
|---|---|---|
| Quelle est la capitale de la France ? (“What is the capital of France?”) | 120 tokens · SHA-256 of the token IDs e45482f0…13d41 | 5 machines |
| Continue la suite : 2, 4, 8, 16, (“Continue the sequence: 2, 4, 8, 16,”) | 256 tokens · SHA-256 of the token IDs 165bae01…dd76a | 3 machines |
| What is the capital of Italy? | 190 tokens · SHA-256 of the token IDs 335da5e0…d663e | 4 machines |
| Continue la suite : 2, 4, 8, 16, (“Continue the sequence: 2, 4, 8, 16,”) | 256 tokens · SHA-256 of the token IDs 1843969a…299b9 | 4 machines |
| Explique en deux phrases pourquoi le ciel est bleu. (“Explain in two sentences why the sky is blue.”) | 256 tokens · SHA-256 of the token IDs f546e89d…5ca72 | 3 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.”) | 256 tokens · SHA-256 of the token IDs e21c931d…a55cf | 3 machines |
| Donne trois nombres premiers entre 10 et 30. (“Give three prime numbers between 10 and 30.”) | 253 tokens · SHA-256 of the token IDs c650a5a8…bb47c | 3 machines |
| Traduis en anglais : la mer est calme ce soir. (“Translate into English: the sea is calm tonight.”) | 256 tokens · SHA-256 of the token IDs bf7d32d4…ea0b2 | 3 machines |
| Quel est le plus grand océan du monde ? (“What is the largest ocean in the world?”) | 256 tokens · SHA-256 of the token IDs f0cd59d0…c112c | 3 machines |
| Écris une phrase de politesse pour finir un e-mail. (“Write a polite sentence to end an email.”) | 256 tokens · SHA-256 of the token IDs b1eed9e4…890f1 | 3 machines |
| Résume en une phrase ce que fait un four à pain. (“Sum up in one sentence what a bread oven does.”) | 256 tokens · SHA-256 of the token IDs 5799d672…8ede6 | 3 machines |
| Continue la suite : 3, 6, 12, 24, (“Continue the sequence: 3, 6, 12, 24,”) | 256 tokens · SHA-256 of the token IDs 0cbb8ff7…a2016 | 3 machines |
The seed file (JSON, 519 bytes)
{"matiere":{"nom":"DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf","octets":4683073504,"sha256":"731ece8d06dc7eda6f6572997feb9ee1258db0784827e642909d9b565641937b","substrat":["hf:bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF/DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf"]},"nom":"r1-qwen-7b","notes":"licence declaree par l hebergeur : mit. 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.
La seule chose qui suit la redistribution est la mention de droit d'auteur et le texte de la licence, à conserver dans toute copie.
La carte amont dit : « This code repository and the model weights are licensed under the MIT License.
DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. » Elle précise aussi que ce modèle est « derived from Qwen-2.5 series, which are originally licensed under Apache 2.0 License » — l'articulation des deux licences est une DÉCLARATION du fournisseur, pas une clause de son texte.
étiquette et carte du dépôt amont lues (étiquette croisée README brut + API) ; le fichier de licence lui-même n'a pas été ouvert