CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.deepseek / DeepSeek-R1-Distill-Llama-70B-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-R1-Distill-Llama-70B-4bit

Date: 2026-11-15Commit: 6b0c127Signed: 2DC28CC7B26A283B ✓

Text generation model with 70.6B parameters. Safetensors weights, 39.7 GB in all. Published by mlx-community under MIT.

70.6B params39.7GBDeepSeek-R1-Distill-Llama-70B-4bitsafetensorspermissive
FactsParams70.6BSize39.7 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit
# manifest sha256 200f6302de39… · 39.7 GB · 15 files
$ fw verify ./DeepSeek-R1-Distill-Llama-70B-4bit mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit
From sourceHosted (signed)mlx-community/DeepSeek-R1-Distill-Llama-70B-4bitLast check: 2026-11-15 05:01 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of DeepSeek-R1-Distill-Llama-70B.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
39.7 GB
Weights
39.7 GB (safetensors)
Parameters
70.6B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
15, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.deepseek
Lineage

Original release from the publisher.

Base model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:01 UTCpassed

Model card

From the publisher at commit 6b0c127. Shown as plain text with links; images open at the publisher.

mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit#

The Model mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Llama-70B using mlx-lm version 0.21.1.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Files

15 files · 39.7 GBWeights 39.7 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 15 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md914 B2065de99ac57094d1adaa1bd85fae63ec3cc5ca2bd649a67cb192278e7812299
config.json1.12 KB3027455f6ce315c983f1955f20d39617c839d417972252a29cdc89c57f6f1106
model-00001-of-00008.safetensors5.27 GBf135e65d7edd73a7ffcfc1e35d3dfdc95a0ad2188a631fbd29ee321168a7da1d
model-00002-of-00008.safetensors5.29 GBbbc147afe5b7375e36a9598e5fcc6eb38743b88e165cdc2e41ed46b39818697d
model-00003-of-00008.safetensors5.29 GB876048f1c4f27f948b6c91731a67fb8d03ed96ed19dd9b9b83e74fb41cc25723
model-00004-of-00008.safetensors5.29 GB9b4b5d9fba18e10b896035076a3fb344a10e7130892d7055d0201d7ef9aa1ecc
model-00005-of-00008.safetensors5.29 GB548011b70e0560323b36b03b7b8e6b1005e4790fc84b7277384d903ec3485ced
model-00006-of-00008.safetensors5.29 GB26e8c20351bce8eb697e15f535bcf1290eb0fa62caf683de449cab212383ae21
model-00007-of-00008.safetensors5.29 GB03d91ab74ab1fa58280ffd84c9479f2313ae7c5142c3934cbd6ade23e3005c77
model-00008-of-00008.safetensors2.65 GB1d0b32f0723385a2ccc64b447f881a1dc3e0627430573f7bc0adafa8fd1023c1
model.safetensors.index.json158 KBdc2f0759c76502dc77a74a06fc9c85a976d16ac12842cfad1d37776c377ea887
special_tokens_map.json485 B59cda48bbe8bab9d61ffb410e6e3c07b6d98bff73cee7c88ff8b51f95f21ab1c
tokenizer.json17.2 MBd91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
tokenizer_config.json52.9 KBd015c5337f32d7bb3281dfc9a61ef11efd71a774c059fed51c91df6370dbaf6f
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
6b0c127e00 pinned now2026-11-15 05:01 UTC15 files · 39.7 GB

Use it

$ fw get mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit
# manifest sha256 200f6302de39… · 39.7 GB · 15 files
$ fw verify ./DeepSeek-R1-Distill-Llama-70B-4bit mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit.json --dir ./DeepSeek-R1-Distill-Llama-70B-4bit $ python3 fw.py verify ./DeepSeek-R1-Distill-Llama-70B-4bit ./mlx-community__DeepSeek-R1-Distill-Llama-70B-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit --revision 6b0c127e00720c480ae36462bb15e71eeb521e80 --local-dir ./DeepSeek-R1-Distill-Llama-70B-4bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit", revision="6b0c127e00720c480ae36462bb15e71eeb521e80") model = AutoModelForCausalLM.from_pretrained("mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit", revision="6b0c127e00720c480ae36462bb15e71eeb521e80", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit --revision 6b0c127e00720c480ae36462bb15e71eeb521e80
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
Inherited from the base model deepseek-ai/DeepSeek-R1-Distill-Llama-70B: the strictest license along the lineage applies. 2026-11-15
Text in
README.md
Text sha256
2065de99ac57094d1adaa1bd85fae63ec3cc5ca2bd649a67cb192278e7812299
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.deepseekSubject: DeepSeek-R1-Distill-Llama-70B-4bitDate: 2026-11-15Commit: 6b0c127Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit
Pinned commit
6b0c127e00720c480ae36462bb15e71eeb521e80
Manifest
DeepSeek-R1-Distill-Llama-70B-4bit.json · .minisig
Manifest sha256
200f6302de391ebe04aef915010e48bbdf2a7c95ad5b13db50aaa62d63c42a0c
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:01 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit.json.minisig $ minisign -Vm DeepSeek-R1-Distill-Llama-70B-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

deepseek-ai/DeepSeek-R1-Distill-Llama-70B · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSeek-R1-Distill-Llama-70B-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit

Related models

All of alt.freeweights.deepseek →
From: timm <huggingface.co/timm>Subject: deepseek_vit_412m.deepseek_v4_1_flash
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-R1-0528-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-V3-0324-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-V3.1-GGUF
From: mlx-community <huggingface.co/mlx-community>Subject: deepseek-ai-DeepSeek-V4-Flash-8bit