CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / Ling-3.1-flash-1019-oQ2e-mtp
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.textSubject:

Ling-3.1-flash-1019-oQ2e-mtp

Date: 2026-11-15Commit: a7e27baSigned: 2DC28CC7B26A283B ✓

Text generation model with 572.1B parameters. Safetensors weights, 193 GB in all. Published by mlx-community under MIT.

572.1B params193GBLing-3.1-flash-1019-oQ2e-mtpsafetensorspermissive
FactsParams572.1BSize193 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get mlx-community/Ling-3.1-flash-1019-oQ2e-mtp
# manifest sha256 8ab1d1cba5cb… · 193 GB · 50 files
$ fw verify ./Ling-3.1-flash-1019-oQ2e-mtp mlx-community/Ling-3.1-flash-1019-oQ2e-mtp
From sourceHosted (signed)mlx-community/Ling-3.1-flash-1019-oQ2e-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
193 GB
Weights
193 GB (safetensors)
Parameters
572.1B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
50, 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 a7e27ba. Shown as plain text with links; images open at the publisher.

Ling-3.1-flash-1019-oQ2e-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 2.701 bits/weight for the complete checkpoint.

Quantization and Bit Distribution#

oQ2e 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 2-bit, group 64547.608B95.716%159.375 GiB2.50
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%179.885 GiB2.701

Storage Breakdown#

ComponentLogical weightsStorage
Language backbone563.946B188.460 GB / 175.517 GiB
MTP head8.174B4.690 GB / 4.367 GiB
Total572.121B193.150 GB / 179.885 GiB

License#

MIT, following the source model.

Files

50 files · 193 GBWeights 193 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 50 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.13 KB07212e9317dd030340d9d14c590f6c7cf061119cdb75dd96993fc9c0dad83250
chat_template.jinja6.04 KBf9beb6cdd406923de4999458056f2cccd016f348ccfa588c0bdb82ee0dbce457
config.json190 KB3f3ca21809ae67fed0237bee01d3a84de7b932ad3def97e7455fff644755e287
configuration_bailing_moe_v3.py4.72 KBf2c048966aec8a2f042cfeb1351f74d51a28589b409c55baae7d24e841c1f6c4
model-00001-of-00039.safetensors5.02 GB09d3843efddd071d014116f61cc4a4bda5dbca906d7ef80114d66d31f53125e3
model-00002-of-00039.safetensors5.03 GB639de27ad8cd1090db2cc8777caf64c282d76bcc9404b83900a37d0682afe279
model-00003-of-00039.safetensors5.00 GB3f0ff55543abd47d3576c99650e45e1132d49927acd40dded91cd9f525b9102e
model-00004-of-00039.safetensors5.55 GBc87e4ad19823a71889cdcbe0b2be55d647eb27cd1264f513e1d8ed8f44eb6bcd
model-00005-of-00039.safetensors5.04 GBd7860672757100432621425c99c245cf7ba98c649a48f78ac89e33b19452a6df
model-00006-of-00039.safetensors5.05 GB0f8ca05bc69f20538c9cd964fb99dde449fddcaf1522d6d9c53acd62f8cca0b0
model-00007-of-00039.safetensors5.04 GBd8749d39c3b8ba4975657f0c2004f7cc790f484dcdad82f9729a2d6f2b10e981
model-00008-of-00039.safetensors5.04 GBab8c3f0f2ad29a606bfa091de672ed410bad8322568db787de833d277d4436ff
model-00009-of-00039.safetensors5.04 GB6f3792d280e04fca6eb7f9b3f589b7f643f6a51fb722d1d5338b630201a92d9f
model-00010-of-00039.safetensors5.05 GBa1e4f25ce13b93a1ca6671b605259b38af033f1535e79f64e77ba7af627f6f7f
model-00011-of-00039.safetensors5.04 GBdb94bee304d239511e78f88bee0a50a1110b516d343b5f4ca76e8f0dd19651c6
model-00012-of-00039.safetensors5.04 GB8e47e2dceb266b52032126e10fada4e4e42c687846abd8f346cfeb8db76fb984
model-00013-of-00039.safetensors5.04 GBad147cb985bd04c9f75a92b78cfe66af107c53f39f7e79e2fd16afc868901d25
model-00014-of-00039.safetensors5.05 GB2be60cb943ef412f70dd746fcabf1ac467b1ddc7a4eaaa88d4109245953eb37d
model-00015-of-00039.safetensors5.04 GB83848a9716135511d71f3447e7fd7bef0a6f65a6b1c03965f5e51b2429273196
model-00016-of-00039.safetensors5.04 GB52986358820020ca5a831b447d9ef1490e665a5e133367f049985751c8d9ebe0
model-00017-of-00039.safetensors5.04 GBa482af2b3242295c051de89855ecaf58a27819053aa2ba62536331636520c866
model-00018-of-00039.safetensors5.05 GB517662f47eb174df87801df41e73a78a63893df6ff42ebda64ea9d2f594b3c34
model-00019-of-00039.safetensors5.04 GBf2f023d19d9fe3970f08d132fc8aefa2c4e80dfced71a8f83b8423631da37361
model-00020-of-00039.safetensors5.04 GBc835627929f31556b33c0866d68d69b8a78bba857d2be1fc06328b4bcd0f2e8a
model-00021-of-00039.safetensors5.04 GBef3dfefbc50f23f1f0e6a71e08c4c4f20c15d2d475da58f58f758924ff12bbc8
model-00022-of-00039.safetensors5.05 GB18e8043a48335ee903d6c44c16b2fa5a9f815932e3b6fb15a09ba087313eb245
model-00023-of-00039.safetensors5.04 GB3b0b740dfcdcbeb7cdd02fbfb83e9bb315d11c5097aeca3812ac7ee0ebb3db2b
model-00024-of-00039.safetensors5.04 GB8d9151e8fe86ed9b07af7e8c4bb768685ec38991b7ad5705dde348e854a4fa5c
model-00025-of-00039.safetensors5.04 GBaf2da083b5d8ce548f2c497a7b0c8f36f78d75d108eada35797c0f037cbc205b
model-00026-of-00039.safetensors5.05 GBd69f373830cf4b05c5b2531015fb22e4ce1455190276d8df5330b5825cb9eee3
model-00027-of-00039.safetensors5.04 GBa222ab572989df8ab137086b70a1c3df2b69220c1f8d913a9ac96dc962791db6
model-00028-of-00039.safetensors5.04 GB5ea10d86257201f33a8aeb88689f82bbe4344fc5e05554e9d4256e7797b891c8
model-00029-of-00039.safetensors5.04 GB6c8edb75e54dd0a8f014e274fcee2e19bf902efd4b6c10697d2f31438989ffd7
model-00030-of-00039.safetensors5.05 GB23b10e90abb761c15b6f1efaa3b539bb0a79779a840ff1bd46d212946dc26ad6
model-00031-of-00039.safetensors5.04 GBaa81acfc1ca4fa7fa4d6b9bae5d6333e5e3bea8de482b6ea166bb78be0d12ec0
model-00032-of-00039.safetensors5.04 GB4e1b04c2a4b514dd69f0670ca9010d5d501a43583584d142389b56c409c2bded
model-00033-of-00039.safetensors5.04 GBe20791172b252a20cd3c61742c07aaedf8a41f76eb067ccb6dc7aba175a3f127
model-00034-of-00039.safetensors5.05 GBa4a6ccba8923c26dbe80a37bbb4cfbf6bcc48619b73418ac883325686ca6c7ef
model-00035-of-00039.safetensors5.04 GB1a1023629e48523c0237f9bfccec0277562767c3308f5558ba77e826a5914bb2
model-00036-of-00039.safetensors5.04 GB1fba033d2aaaa66ed024a661ab87186568b65fa5987164a5731c48912194a02e
model-00037-of-00039.safetensors5.04 GB6a924a13daf9f82724b86bb5cc73e070abe0039a0dd334c76d8e610a920b76b3
model-00038-of-00039.safetensors6.22 GB77976e5410410eaa678519c49c83b22173f358670e1956ee8b801b28e5716968
model-00039-of-00039.safetensors11.1 MBd897137d578c94f7513d93abfc665dd7f865e8a95391434a89ab52dbeea3c32e
model.safetensors.index.json314 KBc9e27e77b0d72bac35f6bfe0b919084ce1896f2f4e14482798ace6e50bb03e34
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
a7e27ba47e pinned now2026-11-15 05:15 UTC50 files · 193 GB

Use it

$ fw get mlx-community/Ling-3.1-flash-1019-oQ2e-mtp
# manifest sha256 8ab1d1cba5cb… · 193 GB · 50 files
$ fw verify ./Ling-3.1-flash-1019-oQ2e-mtp mlx-community/Ling-3.1-flash-1019-oQ2e-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-oQ2e-mtp.json --dir ./Ling-3.1-flash-1019-oQ2e-mtp $ python3 fw.py verify ./Ling-3.1-flash-1019-oQ2e-mtp ./mlx-community__Ling-3.1-flash-1019-oQ2e-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-oQ2e-mtp --revision a7e27ba47ee583f1b79d39280fba2efe0dcde012 --local-dir ./Ling-3.1-flash-1019-oQ2e-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-oQ2e-mtp", revision="a7e27ba47ee583f1b79d39280fba2efe0dcde012") model = AutoModelForCausalLM.from_pretrained("mlx-community/Ling-3.1-flash-1019-oQ2e-mtp", revision="a7e27ba47ee583f1b79d39280fba2efe0dcde012", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Ling-3.1-flash-1019-oQ2e-mtp --revision a7e27ba47ee583f1b79d39280fba2efe0dcde012
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
07212e9317dd030340d9d14c590f6c7cf061119cdb75dd96993fc9c0dad83250
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-oQ2e-mtpDate: 2026-11-15Commit: a7e27baSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Ling-3.1-flash-1019-oQ2e-mtp
Pinned commit
a7e27ba47ee583f1b79d39280fba2efe0dcde012
Manifest
Ling-3.1-flash-1019-oQ2e-mtp.json · .minisig
Manifest sha256
8ab1d1cba5cb2c02926b62dd505552d6ce3a510b037a805abf7e2cc1b7dc3018
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-oQ2e-mtp.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Ling-3.1-flash-1019-oQ2e-mtp.json.minisig $ minisign -Vm Ling-3.1-flash-1019-oQ2e-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-oQ2e-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-oQ2e-mtp.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Ling-3.1-flash-1019-oQ2e-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