CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / Ling-3.1-flash-1019-oQ4e-mtp
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.textSubject:

Ling-3.1-flash-1019-oQ4e-mtp

Date: 2026-11-15Commit: e731d64Signed: 2DC28CC7B26A283B ✓

Text generation model with 572.1B parameters. Safetensors weights, 330 GB in all. Published by mlx-community under MIT.

572.1B params330GBLing-3.1-flash-1019-oQ4e-mtpsafetensorspermissive
FactsParams572.1BSize330 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get mlx-community/Ling-3.1-flash-1019-oQ4e-mtp
# manifest sha256 a07197724c50… · 330 GB · 67 files
$ fw verify ./Ling-3.1-flash-1019-oQ4e-mtp mlx-community/Ling-3.1-flash-1019-oQ4e-mtp
From sourceHosted (signed)mlx-community/Ling-3.1-flash-1019-oQ4e-mtpLast check: 2026-11-15 05:14 UTC
Fine-tune in StudioGet help

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

Quantized of Ling-3.1-flash-1019.

Runs withAIBrixBentoMLCTranslate2ExLlamaV2ExLlamaV3exofastllmFlashInfergpu-unlockKTransformersLitServeLMCacheLMDeployLocalAImistral.rsMLC LLMMooncakeSGLangText Generation WebUItinygradTransformersTriton Inference ServervLLMXinferenceFine-tune withAccelerateAlignment HandbookAxolotlColossal-AIDeepSpeedEasyR1FlashAttentionH2O LLM StudioJAXKerasLiger KernelLitGPTLLaMA-FactoryMegatron-LMms-swiftnanotronOLMo-coreOpenRLHFOumiPEFTPyTorch Lightningsd-scriptsSimpleTunerTorchTitantorchtuneTransformer EngineTRLUnslothverlConvert withAQLMAutoRoundCore ML ToolsExecuTorchGPTQModelLLM CompressormergekitNeural CompressorOliveONNXOptimum QuantoOptimumsafetensorsTensorRT Model OptimizertorchaoEvaluate withAutoevalsDeepEvalEvaluateHELMLightEvallm-evaluation-harnessOpenCompassOpikRagassimple-evalsSWE-benchTruLensWeaveScan withAgentDojoAI Fairness 360DeepTeamDetoxifyFairlearngarakGiskardGuardrailsMCP ScannerModelScanNeMo GuardrailspicklescanpromptfooWorks withAgent Development KitAG2Google AI Edge GalleryAiderany-llmAnythingLLMBAMLbrowser-useCAMELHugging Face Chat UIChatboxCherry StudioClineCodex CLICogneeCrewAIDeerFlowDSPyEnchantedGemini CLIGitHub MCP ServergooseGPT ResearcherGradioGraphitiGuidanceHollamaInstructorKilo CodeLangflowLangGraphLiteLLMLlamaIndexLLMLocalAGILoLLMs WebUIMCP Python SDKMem0MetaGPTNextChatOllama JavaScriptOllama PythonOpenAI Agents SDKopencodeOpenHandsotermOutlinesPage AssistPlaywright MCPPortkey AI GatewayPrivateGPTQwen CodeRWKV RunnerSemantic KernelsmolagentsStrands AgentsVaneXGrammar
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
330 GB
Weights
330 GB (safetensors)
Parameters
572.1B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
67, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: inclusionAI/Ling-3.1-flash-1019

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 05:14 UTCpassed

Model card

From the publisher at commit e731d64. Shown as plain text with links; images open at the publisher.

Ling-3.1-flash-1019-oQ4e-mtp#

This model was quantized using oQ (oMLX v0.7.3rc1) mixed-precision quantization.

A mixed-precision MLX checkpoint of inclusionAI/Ling-3.1-flash-1019, an upgraded version of Ling-3.1-flash with improved reasoning and agentic capabilities. It is a hybrid-linear mixture-of-experts model with 560B total and 25B active parameters, built from 63 KDA linear-attention layers and 9 gated MLA layers, with 512 routed experts of which 8 are active per token. It includes the language model and the MTP (NextN) layer, which oMLX runs as Lightning MTP speculative decoding.

The effective average is 4.615 bits/weight for the complete checkpoint.

Quantization and Bit Distribution#

oQ4e allocates bits by measured layer sensitivity, then rounds each group with an importance matrix (256 samples x 512 tokens, collected layer by layer from the original FP8 weights) and a weighted least-squares refit of its scale and bias.

Storage formatLogical weightsShare of totalTensor storageEffective bits/weight
Affine 4-bit, group 64555.661B97.123%291.094 GiB4.50
Affine 8-bit, group 1281.085B0.190%1.042 GiB8.25
Affine 8-bit, group 6415.333B2.680%15.173 GiB8.50
BF160.041B0.007%0.076 GiB16.00
FP320.000B0.000%0.000 GiB32.00
Total572.121B100%307.385 GiB4.615

Storage Breakdown#

ComponentLogical weightsStorage
Language backbone563.946B325.363 GB / 303.017 GiB
MTP head8.174B4.690 GB / 4.367 GiB
Total572.121B330.052 GB / 307.385 GiB

License#

MIT, following the source model.

Files

67 files · 330 GBWeights 330 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 67 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.06 KBb066d16992849a1b7975aac889bafb6d937a1f3e25325a7e010cb6de11122f05
chat_template.jinja6.04 KBf9beb6cdd406923de4999458056f2cccd016f348ccfa588c0bdb82ee0dbce457
config.json190 KB7f3b28e7fe9b500203f2600728670a06933fd83c572c41fc202fcab6920019e1
configuration_bailing_moe_v3.py4.72 KBf2c048966aec8a2f042cfeb1351f74d51a28589b409c55baae7d24e841c1f6c4
model-00001-of-00056.safetensors5.02 GB09d3843efddd071d014116f61cc4a4bda5dbca906d7ef80114d66d31f53125e3
model-00002-of-00056.safetensors5.03 GB639de27ad8cd1090db2cc8777caf64c282d76bcc9404b83900a37d0682afe279
model-00003-of-00056.safetensors5.00 GB3f0ff55543abd47d3576c99650e45e1132d49927acd40dded91cd9f525b9102e
model-00004-of-00056.safetensors5.22 GB43cb6d18b3aa2466e561258ec744e37aec78b68b8fc3b262b90c039c6afbcfc0
model-00005-of-00056.safetensors6.04 GB5ee465aebfa33e4835e4b0d8881f21ff0ace2168725957e87f80c7b59b8703bc
model-00006-of-00056.safetensors6.04 GB859fcfdd96f1dfd90aea5e6ab021e836aa53aa167339094ab75e75150f9e8cfe
model-00007-of-00056.safetensors6.05 GB83cfb1c4c0fb2b26663033bed0cdeb07810fb6d511e370a38d13d35121672ead
model-00008-of-00056.safetensors6.04 GBc258ad4379c962c9c36839447ab60fbdfe8891475bc35bfe120123c3d2e84d4b
model-00009-of-00056.safetensors6.04 GB367212cba834e36a35865671f0a0800cfd4dd0865cee8e01117a4614b161c907
model-00010-of-00056.safetensors6.04 GB159256712fafb250754fb9e2cb1cbc3c24188009c4aaf79a1c1b989734383f74
model-00011-of-00056.safetensors6.04 GB2363de747df00c2382cbc3e055f9f0dbfafd6c74fc5bf2f736ab1dedb0b8d905
model-00012-of-00056.safetensors6.04 GB020fe6f77090d8669fb11a72e7b777d8625c338657b134bd6b1ef1d4335a2e79
model-00013-of-00056.safetensors6.05 GB2011070d0fbe5dc8762181a6303fe8880caf05e8025626b34c101de43bb0b631
model-00014-of-00056.safetensors6.04 GBbb026fddbf889f8affb8a7bec721d015d7facee494b90d169e58c5066f91e3f3
model-00015-of-00056.safetensors6.04 GBd15e2b75edc3f6abe154698560da64f754de8339a399091b0a58a0084fc8ef09
model-00016-of-00056.safetensors6.04 GB3ee7f877eb03f391e7ad0061b70c5a08c2ab5d592598f1b87bfd18552e676e06
model-00017-of-00056.safetensors6.04 GB4e60cc1fc8ee0178ecfd2bbf50cc8b5805afd9c6e97ae2dd8db29f46ecdacde8
model-00018-of-00056.safetensors6.04 GB9ff34f03ecb13afb977ad16b67ea63418f092d7b63c97323adb293c90964ac98
model-00019-of-00056.safetensors6.05 GBe2abb86bd4646fb8b2d8eb70c2730509717e1aee6c1deec0a13900fbff4f3a94
model-00020-of-00056.safetensors6.04 GB4c9c7eafd62f9ae9e03891b6698b045b991fa87cbbb1a3e98b58f1ccd6c2c45f
model-00021-of-00056.safetensors6.04 GB66d8c4bd3958f1c3676326251edae1e5bcca46cb795b4a0f48c978918b245144
model-00022-of-00056.safetensors6.04 GB8a64627fce4a0b452f56503c955924b73e95dacbb61eb3294f6fafc7da871e4a
model-00023-of-00056.safetensors6.04 GBf20b867adfb5ff76b3523da1f384c380038b453e6cef2d5c57eec23cfd4dc7e3
model-00024-of-00056.safetensors6.04 GB94955883a2a97239333dbd1635cc734e34324a1998b5812dac2a55f560a26132
model-00025-of-00056.safetensors6.05 GB60ca55f942489bba6536c1d917d0532db868ef5a55d36e4d07609a2cd2e04d16
model-00026-of-00056.safetensors6.04 GB2bc0a89b09ba0f9b5f3cf8148fc293f8ac96cbd8ff9042ded8e06f21279518e6
model-00027-of-00056.safetensors6.04 GBa0cd45c0b424ea75e220f715aa0ec0a46d09c28a808b2cf08edef29551da3b44
model-00028-of-00056.safetensors6.04 GB5df83325b0c18c6c04559fff5fcb41785a3df5d0249fd31cc6155ef180bf6920
model-00029-of-00056.safetensors6.04 GB271917af0674317c67cf7348cd2262c01c8973a9543238d153f6fed2ed54e457
model-00030-of-00056.safetensors6.04 GB73ce9984688915851b17ec04f07d565d4f9a4be20cebb19832c481b591317702
model-00031-of-00056.safetensors6.05 GBdd662c5984ed224bfd1a115b2328252640fea1a2f092513e0dd7985c9d475e0d
model-00032-of-00056.safetensors6.04 GB1d3c1ae78b04b0f6f4a8d647e0e50ae104ca0bba6845bc8e587e7ad2ce961310
model-00033-of-00056.safetensors6.04 GB22f58b217767c8c6c360e7b4bba6d5de81c875ba62ea9279d5463055748d670e
model-00034-of-00056.safetensors6.04 GBd7b7f1382909fb7de9730f8a61b6d2e58a8b73466c759249854d99c8a4999c73
model-00035-of-00056.safetensors6.04 GBe6aeee9ac3b831fc8e62b7975cbce5f75e0c8894bee1b288110b8be5886dc339
model-00036-of-00056.safetensors6.04 GBecdd9457eadd244198f13caa6aaecbdacb2fd6886e210760170387cd25b2fb50
model-00037-of-00056.safetensors6.05 GBa1dfe19b8739d748bec2ad3a193272632715615c948f9f50f0b203240b0724f3
model-00038-of-00056.safetensors6.04 GBea6394f06b374ad5a12be5913917ce575142dff7d5eff0a01a996218d0ce7d9e
model-00039-of-00056.safetensors6.04 GB800d4f3e76141f8073dc722ecb2b427b3cdcbf197f2d82d9c20845fba142eeaf
model-00040-of-00056.safetensors6.04 GB7bfa8f6c6919825789fd896cf5dcd606b1218e9693db32b5f0ea6ca1e995a02b
model-00041-of-00056.safetensors6.04 GB2ac574253f543b018f284fe76a33785ce313d52db95904fa34365536def04169
model-00042-of-00056.safetensors6.04 GBace3738c90b7b4c21dbb75b0204b3fc552f9aacd4e616321d0f478b388a8052a
model-00043-of-00056.safetensors6.05 GBfaa3ee2ff1b7006cecb77e968ce8f1be9a5a54db7be17e63cf5bdfe0bcc06535
model-00044-of-00056.safetensors6.04 GB3727feec53abe1f063a04b449d2b131b734c4a55afcb35327d3a96d24760a7b7
model-00045-of-00056.safetensors6.04 GBd5b82d74809849177d17e5a4f47b1fd284c8754b551c74e7fed752ea42f4ae40
model-00046-of-00056.safetensors6.04 GB6ef4e07faa36d728d102adb25ca01510a549c849003d79f931e384134a3540fa
model-00047-of-00056.safetensors6.04 GBe9c77d7b2c9e28bf8ab76c668e11ab8e8da0b67ca55ba0d782b67e2f95251bfb
model-00048-of-00056.safetensors6.04 GB4385d74215dbb792344fd258e2769e1457ec1749f432f3b7ef661d7333182ef1
model-00049-of-00056.safetensors6.05 GB84b1aaebf7959683471e0c1a380bca03360ea5861a9fe2f7d86bd3715d59c463
model-00050-of-00056.safetensors6.04 GB3ece6cb7a746813f76db4e92a3f687546cb72b7a1cba2574ef42c1e011b24827
model-00051-of-00056.safetensors6.04 GB019c72a48f9ff4f317a7dc822dd5544329d655923671b0f8d1fe2cc46a1618e0
model-00052-of-00056.safetensors6.04 GB1aee5bfe3f5b5b58285a78b3cade93f9b1ce78b5520097ab0381b81928af02c1
model-00053-of-00056.safetensors6.04 GBef4b2db40f814e12a9f61b60a541e173a5c3f13882db7ae22ae7ea6c8e31a094
model-00054-of-00056.safetensors6.04 GB496a95c738f4db63cb3c4448aef02475af6a1af1781fb0f8e377d0deb9d8a3c3
model-00055-of-00056.safetensors6.05 GB6b1d3555abcb2ab0018924b84ebf96fdc9beb4e1645a267a4e8643f1f9adb4e7
model-00056-of-00056.safetensors1.52 GBd38dadeebc4e8ae055f7bc14fa8945e5c5a1534f0b0712e1c0cce08ebc7127a5
model.safetensors.index.json314 KB3df00345b69289ca864c6740a472781e9e43d0c25ea836f24a70951c83c78490
modeling_bailing_moe_v3.py74.1 KB8722d34e4617db0d344b925fa2f1157434603f44424bd68107403d456ad31a74
oq_imatrix_report.json50.0 KB7fbae6bd5c388dd18308d23211bf9e1673c221e050a5b9b6b018f598bb62d723
special_tokens_map.json580 B69b63b9f81044ead642d16a5fdc01bcc737dc1183746485c8397ab14d3126614
tokenizer.json12.2 MB40fb9d7d7795b8bd305aeff39ce9963f3f450915b9553f2938e009be9a1fed60
tokenizer_config.json49.7 KB616f1e4ef8474790ea3ac6781a9de2df33f89e0c94a62cefaff7db1808326db1
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e731d64a80 pinned now2026-11-15 05:14 UTC67 files · 330 GB

Use it

$ fw get mlx-community/Ling-3.1-flash-1019-oQ4e-mtp
# manifest sha256 a07197724c50… · 330 GB · 67 files
$ fw verify ./Ling-3.1-flash-1019-oQ4e-mtp mlx-community/Ling-3.1-flash-1019-oQ4e-mtp
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Ling-3.1-flash-1019-oQ4e-mtp.json --dir ./Ling-3.1-flash-1019-oQ4e-mtp $ python3 fw.py verify ./Ling-3.1-flash-1019-oQ4e-mtp ./mlx-community__Ling-3.1-flash-1019-oQ4e-mtp.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Ling-3.1-flash-1019-oQ4e-mtp --revision e731d64a8056924cb80fcdc508ae663febdfae1c --local-dir ./Ling-3.1-flash-1019-oQ4e-mtp
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/Ling-3.1-flash-1019-oQ4e-mtp", revision="e731d64a8056924cb80fcdc508ae663febdfae1c") model = AutoModelForCausalLM.from_pretrained("mlx-community/Ling-3.1-flash-1019-oQ4e-mtp", revision="e731d64a8056924cb80fcdc508ae663febdfae1c", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Ling-3.1-flash-1019-oQ4e-mtp --revision e731d64a8056924cb80fcdc508ae663febdfae1c
Fine-tune in Studio

License

Name
MIT License
Id
MIT
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
b066d16992849a1b7975aac889bafb6d937a1f3e25325a7e010cb6de11122f05
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: Ling-3.1-flash-1019-oQ4e-mtpDate: 2026-11-15Commit: e731d64Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Ling-3.1-flash-1019-oQ4e-mtp
Pinned commit
e731d64a8056924cb80fcdc508ae663febdfae1c
Manifest
Ling-3.1-flash-1019-oQ4e-mtp.json · .minisig
Manifest sha256
a07197724c50f215c98f273a18bcfd49b4d55eee7988400c43cc7c8e6678e742
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:14 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Ling-3.1-flash-1019-oQ4e-mtp.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Ling-3.1-flash-1019-oQ4e-mtp.json.minisig $ minisign -Vm Ling-3.1-flash-1019-oQ4e-mtp.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/Ling-3.1-flash-1019 · 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/Ling-3.1-flash-1019-oQ4e-mtp
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Ling-3.1-flash-1019-oQ4e-mtp.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Ling-3.1-flash-1019-oQ4e-mtp

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