CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / LLaDA2.2-flash-OptiQ-2bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.textSubject:

LLaDA2.2-flash-OptiQ-2bit

Date: 2026-11-15Commit: c7972e3Signed: 2DC28CC7B26A283B ✓

Text generation model with 102.9B parameters. Safetensors weights, 38.9 GB in all. Published by mlx-community under Apache-2.0.

102.9B params38.9GBLLaDA2.2-flash-OptiQ-2bitsafetensorspermissive
FactsParams102.9BSize38.9 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/LLaDA2.2-flash-OptiQ-2bit
# manifest sha256 489d655b638e… · 38.9 GB · 19 files
$ fw verify ./LLaDA2.2-flash-OptiQ-2bit mlx-community/LLaDA2.2-flash-OptiQ-2bit
From sourceHosted (signed)mlx-community/LLaDA2.2-flash-OptiQ-2bitLast check: 2026-11-15 05:15 UTC
Run at homeGet help

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

Quantized of LLaDA2.2-flash.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
38.9 GB
Weights
38.9 GB (safetensors)
Parameters
102.9B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
19, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: inclusionAI/LLaDA2.2-flash

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 05:15 UTCpassed

Model card

From the publisher at commit c7972e3. Shown as plain text with links; images open at the publisher.

LLaDA2.2-flash-OptiQ-2bit#

Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon (no PyTorch, no cloud). Try the Lab · All OptiQ quants · Docs

An OptiQ mixed-precision MLX quant of LLaDA2.2-flash, a ~100B diffusion language model with a 256-routed-expert sparse MoE. This is an extreme 2-bit build.

  • Mixed 2/4-bit static build — per-layer bit-widths assigned to a 2.5 target bits-per-weight.
  • 192 GB bf16 to 36 GB on disk (5.3x).

Requirements#

Needs optiq >= 0.4.4, which ships the vendored llada2_moe decoder (the 256-expert diffusion MoE) and the block-diffusion decode loop. Stock mlx-lm has no llada2_moe arch and cannot load or generate from this repo.

pip install -U optiq

Running it#

LLaDA2 is a masked-diffusion model, not autoregressive — it denoises a canvas block by block. optiq serve detects the arch and routes it through OptiQ's vendored decoder and the block-diffusion decode loop automatically:

optiq serve --model mlx-community/LLaDA2.2-flash-OptiQ-2bit

Then call the OpenAI-compatible endpoint at http://localhost:8000/v1, or use it from the OptiQ Lab and optiq code.

Files

19 files · 38.9 GBWeights 38.9 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 19 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.58 KB64e51bceebeae75c11a78815ef3f69e077fa57ce81802905a719d71f64c2462f
chat_template.jinja5.83 KB17fbfd9f15607136dfb070154885364413aa1af8fe8942dcf46b1c8a80c4fdf0
config.json61.3 KB344558cc93b78d2c8737f21049fd54329eb707307e93855c7e52d9cd1f855960
configuration_llada2_moe.py3.33 KB8ad02902146ca73fbf21a95c2802cfbe2c5059a6a06a4d065facdd50c2ce5fb9
generation_config.json151 Ba16c96226728a133ea949dbdb377cd2816233c61c532e37347e700287b36d363
model-00001-of-00008.safetensors5.36 GB77fab94aab7eb0490bd4d49db680489ef7803cf408d4f7b0f2e1b935efc5bae9
model-00002-of-00008.safetensors5.12 GBfab7251808409a88a34d5846ebcb7e74d1577b427bea2e7860998a6a22940c03
model-00003-of-00008.safetensors5.19 GB3cf834927aa65a4b5e47ec1336f1c89536db97035168b06712f12b10e1398056
model-00004-of-00008.safetensors5.19 GB65a7c4c09e03aef3f71c2ff6521cbe6db6fd024c8cada7b3e16966491807418c
model-00005-of-00008.safetensors5.19 GBd258fb825d14e76ea4e2ce8745dc66109d188e6dbba6eceaf55fa280cd000c05
model-00006-of-00008.safetensors5.12 GBe0e20e3812906715c99e0778edd2241767e4bd8bfaf277c7771310109c2b5322
model-00007-of-00008.safetensors4.89 GB7e8ff95e90f1e0d98f83d4fe2a3714e54fe9536b1dd395cbc66f506ede6f4238
model-00008-of-00008.safetensors2.82 GBc2d5229511d26a70ada887279180388ba9db5a7496f53645abbd35fcf7f8f2c5
model.safetensors.index.json89.2 KB8cdd23680f078eb2f796cdabfedfbfa690eab1c17f52097de5d62a272500e270
modeling_llada2_moe.py76.1 KBab246877017cefd93821f7498a74ef0a6af9e4cfb8295d750491601a3f6e9a59
optiq_metadata.json24.8 KBcaecaa291c97fb5995c61d95cdc260242f09c24c7ec1214010073c06599ccdae
tokenizer.json12.2 MBa10ebccef6bd33380bbb262e3280c19a213efd4cf1195c0dfc3b3b3c40041189
tokenizer_config.json528 Bdd04243b36ea5ad15cd2a22558100b5ff637bc08fffc879b28eb543d37e5e089
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
c7972e32b4 pinned now2026-11-15 05:15 UTC19 files · 38.9 GB

Use it

$ fw get mlx-community/LLaDA2.2-flash-OptiQ-2bit
# manifest sha256 489d655b638e… · 38.9 GB · 19 files
$ fw verify ./LLaDA2.2-flash-OptiQ-2bit mlx-community/LLaDA2.2-flash-OptiQ-2bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/LLaDA2.2-flash-OptiQ-2bit.json --dir ./LLaDA2.2-flash-OptiQ-2bit $ python3 fw.py verify ./LLaDA2.2-flash-OptiQ-2bit ./mlx-community__LLaDA2.2-flash-OptiQ-2bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/LLaDA2.2-flash-OptiQ-2bit --revision c7972e32b4a208afc8abab9104da0d429ae36d02 --local-dir ./LLaDA2.2-flash-OptiQ-2bit
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/LLaDA2.2-flash-OptiQ-2bit", revision="c7972e32b4a208afc8abab9104da0d429ae36d02") model = AutoModelForCausalLM.from_pretrained("mlx-community/LLaDA2.2-flash-OptiQ-2bit", revision="c7972e32b4a208afc8abab9104da0d429ae36d02", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/LLaDA2.2-flash-OptiQ-2bit --revision c7972e32b4a208afc8abab9104da0d429ae36d02
Run at home

License

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
64e51bceebeae75c11a78815ef3f69e077fa57ce81802905a719d71f64c2462f
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.textSubject: LLaDA2.2-flash-OptiQ-2bitDate: 2026-11-15Commit: c7972e3Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/LLaDA2.2-flash-OptiQ-2bit
Pinned commit
c7972e32b4a208afc8abab9104da0d429ae36d02
Manifest
LLaDA2.2-flash-OptiQ-2bit.json · .minisig
Manifest sha256
489d655b638ede8d298bfd9565a70cbe35990c22028aa14477003d4d5a718e38
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:15 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/LLaDA2.2-flash-OptiQ-2bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/LLaDA2.2-flash-OptiQ-2bit.json.minisig $ minisign -Vm LLaDA2.2-flash-OptiQ-2bit.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

inclusionAI/LLaDA2.2-flash · 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/LLaDA2.2-flash-OptiQ-2bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. LLaDA2.2-flash-OptiQ-2bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/LLaDA2.2-flash-OptiQ-2bit

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B