CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / Ling-3.1-flash-1019-oQ3e-mtp
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.textSubject:

Ling-3.1-flash-1019-oQ3e-mtp

Date: 2026-11-15Commit: b3da74eSigned: 2DC28CC7B26A283B ✓

Text generation model with 572.1B parameters. Safetensors weights, 262 GB in all. Published by mlx-community under MIT.

572.1B params262GBLing-3.1-flash-1019-oQ3e-mtpsafetensorspermissive
FactsParams572.1BSize262 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get mlx-community/Ling-3.1-flash-1019-oQ3e-mtp
# manifest sha256 d711f64ea4bf… · 262 GB · 57 files
$ fw verify ./Ling-3.1-flash-1019-oQ3e-mtp mlx-community/Ling-3.1-flash-1019-oQ3e-mtp
From sourceHosted (signed)mlx-community/Ling-3.1-flash-1019-oQ3e-mtpLast check: 2026-11-15 05:15 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
262 GB
Weights
262 GB (safetensors)
Parameters
572.1B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
57, 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 05:15 UTCpassed

Model card

From the publisher at commit b3da74e. Shown as plain text with links; images open at the publisher.

Ling-3.1-flash-1019-oQ3e-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 3.658 bits/weight for the complete checkpoint.

Quantization and Bit Distribution#

oQ3e 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 3-bit, group 64547.608B95.716%223.125 GiB3.50
Affine 4-bit, group 648.053B1.408%4.219 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%243.635 GiB3.658

Storage Breakdown#

ComponentLogical weightsStorage
Language backbone563.946B256.911 GB / 239.267 GiB
MTP head8.174B4.690 GB / 4.367 GiB
Total572.121B261.601 GB / 243.635 GiB

License#

MIT, following the source model.

Files

57 files · 262 GBWeights 262 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 57 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.13 KB38ed344ae81371133b419b363149698afe6e8339b56724b1b8c071cc40e20e4c
chat_template.jinja6.04 KBf9beb6cdd406923de4999458056f2cccd016f348ccfa588c0bdb82ee0dbce457
config.json190 KB157d14c34b35c6864f4502fff2a3c8d85cf33dcadc9b36bddf577c4565e8e4c8
configuration_bailing_moe_v3.py4.72 KBf2c048966aec8a2f042cfeb1351f74d51a28589b409c55baae7d24e841c1f6c4
model-00001-of-00046.safetensors5.02 GB09d3843efddd071d014116f61cc4a4bda5dbca906d7ef80114d66d31f53125e3
model-00002-of-00046.safetensors5.03 GB639de27ad8cd1090db2cc8777caf64c282d76bcc9404b83900a37d0682afe279
model-00003-of-00046.safetensors5.00 GB3f0ff55543abd47d3576c99650e45e1132d49927acd40dded91cd9f525b9102e
model-00004-of-00046.safetensors5.72 GBa99be97cd1e496d3a4c9c7054c7cca5e5a0d56152bec4da12d71a4dfb606e880
model-00005-of-00046.safetensors5.88 GB87832afff1639f2c1694df58aacafbb7c76cea7513b33040fb486fade70f0902
model-00006-of-00046.safetensors5.89 GB710dff4da266aee8129bf3d92a97bb0225a84e11da13a88afa511be350b36c6e
model-00007-of-00046.safetensors5.87 GBb818b7624850871807e2bb1c5759288f5590f5d0b11bcb1479eef165be579914
model-00008-of-00046.safetensors5.88 GB35a76e2c2fab7925ea8f09ef076eb21b4f725ac5a2c74b76db3489dbe1166cc7
model-00009-of-00046.safetensors5.88 GB11ce4bc873c232e050e6422b077d4e1427144e911e5f8ffef56819b260d3f087
model-00010-of-00046.safetensors5.87 GB33d7d247bde5a700f8bc621a950dd302dd65e7359382029dfa3d350b0aace77a
model-00011-of-00046.safetensors5.89 GBcfed8fe6758474701cee8835614d29ed60451a90f1012dd1fe970f1dfe39f3da
model-00012-of-00046.safetensors5.88 GBa26aed433edb782a6fc8ed7432093f789f4d55993c6e15d112806e0d5425a56e
model-00013-of-00046.safetensors5.87 GBa9a1f8711629c773200a096c92b7f2426a024b32054de40cbadf5d9d0607cd4c
model-00014-of-00046.safetensors5.88 GB4e44de51c4ee63aeedf73e9dcefeecc8c11ff68f4fa9db781021a129116586ef
model-00015-of-00046.safetensors5.88 GB6bdabb0e1a2b0d46e2623bb3484348c56a81a4d97ec67aa7d64f1bf275433d2b
model-00016-of-00046.safetensors5.88 GBa7106687f5dbff95a5d5e65a2fb9aeb561f7a60982a9de60c1ec0c2479b1a7f5
model-00017-of-00046.safetensors5.88 GBec6975a7bd3699dbb804483904460bf00820420f2dec056a12cc489657766eda
model-00018-of-00046.safetensors5.88 GBce10e3ad7d5b1779f6e51526a473185f9c38552c17c655eb02f3e0288ff98d09
model-00019-of-00046.safetensors5.87 GB43af3af5e9159f7a189ce7031e2b1c984aee19f17342b07dd2af847c925bac55
model-00020-of-00046.safetensors5.88 GBa8bdbe9ee41a516f17221219893cbd990191379db74dc96950ed507540de072f
model-00021-of-00046.safetensors5.89 GBb17c19d9058285e6585cdb915ed05c9c996ab6d89132b9ed7de9a814446dd27c
model-00022-of-00046.safetensors5.87 GB27dfcbdf1cc8f9d2ee9f5be4c4e095e0317c6fbc8786480b7f7e1f13542b3106
model-00023-of-00046.safetensors5.88 GBbb94ee425b018cdd57d210cc1bd8901c16692717720411eaeecc2000167dd92e
model-00024-of-00046.safetensors5.88 GB536ea2358587c9c12065b04c704efb7deb1d770f789a78a2da408ba3820ab611
model-00025-of-00046.safetensors5.87 GB8406ce1f42b14b074d99b705318bf9e0b38b1ba0e28b67b5b568040e7bbdd360
model-00026-of-00046.safetensors5.89 GB2b8b9db9fd1e2ad0dc5755bee29f6df7d3ba3b18867ac7ff68e90faf518f8272
model-00027-of-00046.safetensors5.88 GB59010e591ac82aaccfb4aa0a78dd85c31893d79e7c4d99926ccb98e8f7b9b93b
model-00028-of-00046.safetensors5.87 GB55a0b66dc7851c27416cf5f9672877644070b7503119d59b163bdef27db52789
model-00029-of-00046.safetensors5.88 GB2ceb593c9918486bb6024d6cfad9ee5afe9b1acd298960c50a120715731e4169
model-00030-of-00046.safetensors5.89 GB5f1851401049be2bde2ee95d9a3d48453cff9f429d709546143ba03f5d1ad7cd
model-00031-of-00046.safetensors5.87 GB2d9646481eee08add994525f297a0f73537b576f355f220d321da2d08408c268
model-00032-of-00046.safetensors5.88 GBe252378a2f7b2a260b6e4085c16e072028da9044ffdcc92e9a7daed1f51966a8
model-00033-of-00046.safetensors5.88 GB7c8bfecacec277f3ee4321eee8dcfa3d5dcc91a100a2560b5cecbc9cffe46f7a
model-00034-of-00046.safetensors5.87 GB53efa6ea8ee04dd0373199c059cbc717506d84e37131abee37f1f7da31993592
model-00035-of-00046.safetensors5.89 GBf748c1f9967ef20dc6b289b979cbd6491687de225a9fa76e5626447ceb47f5fc
model-00036-of-00046.safetensors5.88 GB4bcb5606eb75db1ce260142b577a5c7f14af3f8d9807ba8f0e3109f771c12323
model-00037-of-00046.safetensors5.87 GB40d6a26f214b8c8b924633b8b5c449b4a15524be010b0934a08be718fa5f6f2c
model-00038-of-00046.safetensors5.88 GB3e44691e73269398839283e45523cab0f45d3387c6eda4f1e2791e3847a3091a
model-00039-of-00046.safetensors5.88 GBcf246a016951e8989e04ef5b3a50319f4ba15261ffda1b2e066c68d832d12877
model-00040-of-00046.safetensors5.88 GB253ebdfa1a391019fc0e4f3332dc73555a5eb7496c94af0adb70eaed9a60f9a0
model-00041-of-00046.safetensors5.88 GB3af74181b09e58518eb08ad85ee325be12888633b9bd59fb2ceb7cb39ebc1f77
model-00042-of-00046.safetensors5.88 GBb3eb9826e76994909c1f5f09445e54e5551fea2e3fab29a0f3d0b82dec963062
model-00043-of-00046.safetensors5.87 GBe5b59b17d62b3e8ffeff733ccedc4bafaf29ca40f527b25eac4085d93d1bc1cc
model-00044-of-00046.safetensors5.88 GB829b1db1f068641f95717b0443bcbbfc1df4998bcc9bbe5c92659291494bb97c
model-00045-of-00046.safetensors5.72 GB2d2b3bca1d7aa1dd087e77f527691c5c8d330aaded121b76434a6bd5c7a2a67a
model-00046-of-00046.safetensors11.1 MBd897137d578c94f7513d93abfc665dd7f865e8a95391434a89ab52dbeea3c32e
model.safetensors.index.json314 KB19b4cd828ef8b9098405cada38a72c998523e77caf689689abb82b13c77fb286
modeling_bailing_moe_v3.py74.1 KB8722d34e4617db0d344b925fa2f1157434603f44424bd68107403d456ad31a74
oq_imatrix_report.json50.0 KBf07fb6e79991414d214547f39ff6d156faa5909fe6c8aae44620bee13460e961
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
b3da74e64c pinned now2026-11-15 05:15 UTC57 files · 262 GB

Use it

$ fw get mlx-community/Ling-3.1-flash-1019-oQ3e-mtp
# manifest sha256 d711f64ea4bf… · 262 GB · 57 files
$ fw verify ./Ling-3.1-flash-1019-oQ3e-mtp mlx-community/Ling-3.1-flash-1019-oQ3e-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-oQ3e-mtp.json --dir ./Ling-3.1-flash-1019-oQ3e-mtp $ python3 fw.py verify ./Ling-3.1-flash-1019-oQ3e-mtp ./mlx-community__Ling-3.1-flash-1019-oQ3e-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-oQ3e-mtp --revision b3da74e64c2a0cfc97b819c066230a502a4dadf0 --local-dir ./Ling-3.1-flash-1019-oQ3e-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-oQ3e-mtp", revision="b3da74e64c2a0cfc97b819c066230a502a4dadf0") model = AutoModelForCausalLM.from_pretrained("mlx-community/Ling-3.1-flash-1019-oQ3e-mtp", revision="b3da74e64c2a0cfc97b819c066230a502a4dadf0", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Ling-3.1-flash-1019-oQ3e-mtp --revision b3da74e64c2a0cfc97b819c066230a502a4dadf0
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
38ed344ae81371133b419b363149698afe6e8339b56724b1b8c071cc40e20e4c
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-oQ3e-mtpDate: 2026-11-15Commit: b3da74eSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Ling-3.1-flash-1019-oQ3e-mtp
Pinned commit
b3da74e64c2a0cfc97b819c066230a502a4dadf0
Manifest
Ling-3.1-flash-1019-oQ3e-mtp.json · .minisig
Manifest sha256
d711f64ea4bff5d698d7c872ead558784320576215fef1e8287aa40cd8bcd69a
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/Ling-3.1-flash-1019-oQ3e-mtp.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Ling-3.1-flash-1019-oQ3e-mtp.json.minisig $ minisign -Vm Ling-3.1-flash-1019-oQ3e-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-oQ3e-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-oQ3e-mtp.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Ling-3.1-flash-1019-oQ3e-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