From: mlx-community <huggingface.co/mlx-community> Newsgroups: alt.freeweights.embedSubject: all-MiniLM-L6-v2-4bit Date: 2026-11-15Commit: 128ca2dSigned: 2DC28CC7B26A283B ✓ Sentence similarity model with 23M parameters. Safetensors weights, 13.9 MB in all. Published by mlx-community under Apache-2.0.
23M params 13.9 MB all-MiniLM-L6-v2-4bit safetensors permissive Facts Params 23M Size 13.9 MB Formats safetensors Task sentence similarity License Apache-2.0 From sourcepermissive
fw
$ fw get mlx-community/all-MiniLM-L6-v2-4bit
# manifest sha256 059edb2be7a8… · 13.9 MB · 14 files
$ fw verify ./all-MiniLM-L6-v2-4bit mlx-community/all-MiniLM-L6-v2-4bit
From sourceHosted (signed) mlx-community/all-MiniLM-L6-v2-4bit Last check: 2026-11-15 02:49 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Overview
Size 13.9 MB
Weights 12.8 MB (safetensors)
Parameters 23M
Formats safetensors
Task sentence similarity
License Apache-2.0 (permissive)
Files 14, each with a sha256
Publisher mlx-community
Added 2026-11-15
Section alt.freeweights.embed
Lineage
Original release from the publisher.
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
Badge Host Last check Result From sourcehuggingface.co 2026-11-15 02:49 UTC passed
Model card From the publisher at commit
128ca2d . Shown as plain text with links; images open at the publisher.
The Model mlx-community/all-MiniLM-L6-v2-4bit was converted to MLX format from sentence-transformers/all-MiniLM-L6-v2 using mlx-lm version 0.0.3 .
Use with mlx#
pip install mlx-embeddings Copy
from mlx_embeddings import load, generate
import mlx.core as mx
model, tokenizer = load("mlx-community/all-MiniLM-L6-v2-4bit")
# For text embeddings
output = generate(model, processor, texts=["I like grapes", "I like fruits"])
embeddings = output.text_embeds # Normalized embeddings
# Compute dot product between normalized embeddings
similarity_matrix = mx.matmul(embeddings, embeddings.T)
print("Similarity matrix between texts:")
print(similarity_matrix)
Copy Files 14 files · 13.9 MB Weights 12.8 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256 File Size sha256 .gitattributes 1.52 KB 11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361 README.md 1.49 KB 56ab5d8da459eaf85d5f95cf3f5069ed32357158f86cdf92317f59e75f3be605 config.json 674 B a36c0ff7777341d61d43b1ecfb8c97c858c034da40acbcff2a8b1a406a09e229 config_sentence_transformers.json 116 B 061ca9d39661d6c6d6de5ba27f79a1cd5770ea247f8d46412a68a498dc5ac9f3 data_config.json 39.3 KB 32edcb108fc2516b920734a862ae0692bcae1c5d45d5f8d972cb0d53434a4c54 model.safetensors 12.8 MB 47d121d5e99f8e21076ede2dd78a3884adcd0e7584fe4920f44b3e8bb60a1cae model.safetensors.index.json 13.5 KB 1edb461fa3ad43038d48e8226e67b53c0e49bc2344c59eb32ab6f4a6a33aa607 modules.json 349 B 84e40c8e006c9b1d6c122e02cba9b02458120b5fb0c87b746c41e0207cf642cf sentence_bert_config.json 53 B fc1993fde0a95c24ec6c022539d41cf6e2f7c9721e5415d6fb6897472a9cd4b7 special_tokens_map.json 695 B 5d5b662e421ea9fac075174bb0688ee0d9431699900b90662acd44b2a350503a tokenizer.json 712 KB da0e79933b9ed51798a3ae27893d3c5fa4a201126cef75586296df9b4d2c62a0 tokenizer_config.json 1.46 KB ccb4eb21a03e1442ee5c3f85431b9c307960a04579942537d74778dc8080a48c train_script.py 13.2 KB f9b98b9d203d728cbf93ccdbae84131ab926541b56196f11d1385fed0b4d1a07 vocab.txt 232 KB 07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents 128ca2da88 pinned now 2026-11-15 02:49 UTC 14 files · 13.9 MB
Use it fw
$ fw get mlx-community/all-MiniLM-L6-v2-4bit
# manifest sha256 059edb2be7a8… · 13.9 MB · 14 files
$ fw verify ./all-MiniLM-L6-v2-4bit mlx-community/all-MiniLM-L6-v2-4bitfw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/all-MiniLM-L6-v2-4bit.json --dir ./all-MiniLM-L6-v2-4bit
$ python3 fw.py verify ./all-MiniLM-L6-v2-4bit ./mlx-community__all-MiniLM-L6-v2-4bit.json Copyhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/all-MiniLM-L6-v2-4bit --revision 128ca2da88d925829a17fb5ddfdc86b42eb58fb2 --local-dir ./all-MiniLM-L6-v2-4bit Copytransformers Load the weights in Python.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from transformers import AutoModel, AutoTokenizer
tok = AutoTokenizer.from_pretrained("mlx-community/all-MiniLM-L6-v2-4bit", revision="128ca2da88d925829a17fb5ddfdc86b42eb58fb2")
model = AutoModel.from_pretrained("mlx-community/all-MiniLM-L6-v2-4bit", revision="128ca2da88d925829a17fb5ddfdc86b42eb58fb2", device_map="auto") Copysentence-transformers Embed text with sentence-transformers.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("mlx-community/all-MiniLM-L6-v2-4bit", revision="128ca2da88d925829a17fb5ddfdc86b42eb58fb2")
vectors = model.encode(["Hello"]) CopyLicense Name Apache License 2.0 Id Apache-2.0 Class Permissive Redistribution yes Listing Hosted (signed) Decided License as declared by the publisher. No person read it. 2026-11-15 Text in README.md Text sha256 56ab5d8da459eaf85d5f95cf3f5069ed32357158f86cdf92317f59e75f3be605 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.embedSubject: all-MiniLM-L6-v2-4bit Date: 2026-11-15Commit: 128ca2dSigned: 2DC28CC7B26A283B ✓ Upstream mlx-community/all-MiniLM-L6-v2-4bit Pinned commit 128ca2da88d925829a17fb5ddfdc86b42eb58fb2 Manifest all-MiniLM-L6-v2-4bit.json · .minisig Manifest sha256 059edb2be7a8bcc11b1d885fbe12074ed112980f76d4d3b9c9d0ae0bf4cc0ee9 Signature minisign, Ed25519, key 2DC28CC7B26A283B Created 2026-11-15 02:49 UTC Generator freeweights-manifest/0.1.0 Takedowns None.
How to verify
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/all-MiniLM-L6-v2-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/all-MiniLM-L6-v2-4bit.json.minisig
$ minisign -Vm all-MiniLM-L6-v2-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file> # compare with the Files tab Copy
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 No related models in this catalog. Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/all-MiniLM-L6-v2-4bit Copy
Open in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
23M params 795 MB all-MiniLM-L6-v1 onnx openvino safetensors permissive Facts Params 23M Size 795 MB Formats onnx, openvino, safetensors Task sentence similarity License Apache-2.0 From sourcepermissive flip From: sentence-transformers <huggingface.co/sentence-transformers> Subject: all-MiniLM-L6-v1 23M params 977 MB all-MiniLM-L6-v2 onnx openvino safetensors permissive Facts Params 23M Size 977 MB Formats onnx, openvino, safetensors Task sentence similarity License Apache-2.0 From sourcepermissive flip From: unsloth <huggingface.co/unsloth> Subject: all-MiniLM-L6-v2 109M params 3.82 GB all-mpnet-base-v1 onnx openvino safetensors permissive Facts Params 109M Size 3.82 GB Formats onnx, openvino, safetensors Task sentence similarity License Apache-2.0 From sourcepermissive flip From: sentence-transformers <huggingface.co/sentence-transformers> Subject: all-mpnet-base-v1 110M params 4.28 GB allenai-specter onnx openvino safetensors permissive Facts Params 110M Size 4.28 GB Formats onnx, openvino, safetensors Task sentence similarity License Apache-2.0 From sourcepermissive flip From: sentence-transformers <huggingface.co/sentence-transformers> Subject: allenai-specter 109M params 4.70 GB bert-base-nli-max-tokens onnx openvino safetensors permissive Facts Params 109M Size 4.70 GB Formats onnx, openvino, safetensors Task sentence similarity License Apache-2.0 From sourcepermissive flip From: sentence-transformers <huggingface.co/sentence-transformers> Subject: bert-base-nli-max-tokens 109M params 4.70 GB bert-base-nli-stsb-mean-tokens onnx openvino safetensors permissive Facts Params 109M Size 4.70 GB Formats onnx, openvino, safetensors Task sentence similarity License Apache-2.0 From sourcepermissive flip From: sentence-transformers <huggingface.co/sentence-transformers> Subject: bert-base-nli-stsb-mean-tokens