CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3.8-Flash-Next-oQ8e-mtp
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.8-Flash-Next-oQ8e-mtp

Date: 2026-11-15Commit: 2a9de02Signed: 2DC28CC7B26A283B ✓

Model with 180B parameters. Safetensors weights, 195 GB in all. Published by mlx-community under Qwen-Community-1.0 (custom).

180B params195GBQwen3.8-Flash-Next-oQ8e-mtpsafetensorscustom terms
FactsParams180BSize195 GBFormatssafetensorsTasknot taggedLicenseQwen-Community-1.0 (custom)From sourcecustom termsread terms
# custom terms: read the license before you download
$ fw get mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp
# manifest sha256 17906d2062a3… · 195 GB · 50 files
$ fw verify ./Qwen3.8-Flash-Next-oQ8e-mtp mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp
From sourceHosted (signed)mlx-community/Qwen3.8-Flash-Next-oQ8e-mtpLast check: 2026-11-15 05:07 UTC
Get help

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

Quantized of Qwen3.8-Flash-Next.

Works with

Run8Fine-tune7Convert8Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
195 GB
Weights
195 GB (safetensors)
Parameters
180B
Formats
safetensors
Task
not tagged
License
Qwen-Community-1.0 (custom) (custom)
Files
50, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3.8-Flash-Next

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 05:07 UTCpassed

Model card

From the publisher at commit 2a9de02. Shown as plain text with links; images open at the publisher.

Qwen3.8-Flash-Next-oQ8e-mtp#

This model was quantized using oQ in oMLX v0.6.4. oQe (imatrix). MTP kept.

Quantization details#

  • Model type: qwen4_exp
  • Bits: 8
  • Group size: 64
  • Format: MLX safetensors
  • oMLX: Jundot v0.6.4 (source)
  • Parameters: 125B total, 6B activated, 51B n-gram embedding, 4B MTP
  • MTP: preserved (76 mtp.* tensors)
  • Source: Qwen/Qwen3.8-Flash-Next, converted to MLX, then oQe with preserve_mtp

Benchmark#

Apple M3 Ultra, 256 GB. oMLX 0.6.4. Thinking off, temperature 0, Lightning MTP depth 3. oQ4e is Jundot/Qwen3.8-Flash-Next-oQ4e-mtp on the same machine.

Write speed is how fast the reply is generated (generation_tokens_per_second). Read speed is how fast the prompt is ingested (prompt_tokens_per_second).

Coding task: write a Python Fibonacci function, no comments. All three packs stopped on their own.

oQ4eoQ6eoQ8e
Time to completion1.74 s2.07 s2.57 s
Time to first token0.51 s0.64 s0.67 s
Tokens written798080
Write speed (tok/s)64.456.142.1
Read speed (tok/s)51.240.338.9

Longer prompts (256-token generation cap):

Write speed (tok/s)#
ContextoQ4eoQ6eoQ8e
Short code64.456.142.1
4K56.544.941.9
8K56.344.843.7
16K52.948.347.5
Read speed (tok/s)#
ContextoQ4eoQ6eoQ8e
Short code51.240.338.9
4K732597581
8K772728716
16K729785763

Raw timings: bench.json (this pack) and bench-compare.json (all three).

Files

50 files · 195 GBWeights 195 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 50 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
LICENSE3.23 KBa0dc422560841fd68e06d974907f8b4c709bca44a67daad2b528437bdf676c08
README.md2.09 KBbe38e1a11f3a0fd9eea53132ebde4b5e8a9c1379e0e4419d182477b61311e57e
bench-compare.json1.77 KBfcaac8283d5a97e2041afc8f52cf2b0ec64f93b41a3bf0be3cced2256e1ab1ee
bench.json2.47 KB4b1bed953750505b475aec1caedddd5292da927ae631ab68c81bf8afa2587d1c
chat_template.jinja8.95 KBc3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041
config.json132 KB88793ae9905553224f329afde5859dfeb2e60401eb60e19dd0d6f222a3d7429d
generation_config.json202 Be70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e
model-00001-of-00036.safetensors5.28 GBcd14f6efc3344cb505ddc56167363671ddaba63cceebc4df79df2f2cc8575d90
model-00002-of-00036.safetensors5.39 GB5bcfd9fd2be4247b77d06970e4095c0598f9fd72639667186d96995dae1a6cb2
model-00003-of-00036.safetensors5.40 GBbb3098c3e3182f97cd401d33beb532c64ddeb335551bb57b5614ca8cce4858b5
model-00004-of-00036.safetensors5.40 GBfca01f04401162046f861481f126dec54a9d2140e8dbf4023d25a074c254bad4
model-00005-of-00036.safetensors5.40 GBeb88cb8475208232a08f2bda5de8370f41583c1f7bdfd7fb0bb6ada3ffaaab38
model-00006-of-00036.safetensors5.40 GB351e2b3673fa8cc25e3fa0548b7c448e958bb69198f9fb205558163fe5438a39
model-00007-of-00036.safetensors5.40 GBbf00e44d2ea942a418da48eb87dbb5d65bbc4d87c14d49f5044bc98222c5f625
model-00008-of-00036.safetensors5.40 GB415e66029145be8f17331fe303d61470654af958c2e837f3c66896f5d2c1b14b
model-00009-of-00036.safetensors5.40 GBff3424a5543f7d4e66a55c1186bbdd204116aeec8a87d13d66d463924e554092
model-00010-of-00036.safetensors5.40 GBf5619cea829dafe96aeb5dc9c70413c379bd405a8eababb73e647bf91fc63d8b
model-00011-of-00036.safetensors5.40 GB52037bffcbfae22e136db4452aff4af061a9741f431875fbb8f735faad1e8e8d
model-00012-of-00036.safetensors5.44 GB6811dd364244efb4590095c72730eb96c8156af59fac6deb5c70f0fc2d5c8098
model-00013-of-00036.safetensors5.51 GB979a784115e060c262d486ed2f306ab8497854032fda68b10442d7a7fab45dd8
model-00014-of-00036.safetensors5.51 GB7b4a2df743d8581336eea81773a94d4a25b6721dc507bf39d5ed0d2a60a6d4a0
model-00015-of-00036.safetensors5.51 GBd0a2dceae770d148add5fa56fd5fe0575a1fd7c10bacb106d1fe6408b0d8db6c
model-00016-of-00036.safetensors5.58 GB2f350bf95bb1029d51ba7baae849dcdb20aacbe9032c4068b8267466e95c6e52
model-00017-of-00036.safetensors5.44 GBf80b87c2c999157f7df05e6a06557dc3d3ae9445698dbd8dc0681afadb1cf210
model-00018-of-00036.safetensors5.51 GBca1e10ff119105c166dff249eb84e6b33cb74f188a76e355dde9c7cddbf2e1a4
model-00019-of-00036.safetensors5.51 GBb73da7b7b0b1b0a247a497585f63574ac25b5769c103940f927f77ca280485ea
model-00020-of-00036.safetensors5.51 GBf2464c016ebbcb55b91ae29218a07b6123e8fcbcb0e53e96c260f9f49af05379
model-00021-of-00036.safetensors5.51 GB6e3da7b105d3f7ba9ce4d5255eb1c541ae35fc31010373184c13b66c02068699
model-00022-of-00036.safetensors5.51 GB77aee259218d25fdfb481a5a9c11cc4af893d65452b997d7ad914bdba3f61021
model-00023-of-00036.safetensors5.51 GB8496db5a177a9b9619a1ffdf278a930b978fba9a47e17a1a33ce707d504d79ba
model-00024-of-00036.safetensors5.51 GB2fc1c6781e8689935b9177cdbc2e6180113b4b5ac392872ce47d50b0e7371a1a
model-00025-of-00036.safetensors5.51 GBb6cb36f12564d4721279eebd3105e67000ff343f63d4868329a4600b7e8ee18c
model-00026-of-00036.safetensors5.51 GB27a6c4baa5926c790a93c8dec584702b40fbfe9d105b7a3db408b696f42cd1a1
model-00027-of-00036.safetensors5.51 GB2bd223600f136b92d7534bc5d17f07d3a7e9cedff36c45ec3525969807d242c7
model-00028-of-00036.safetensors5.51 GB5bb3270b95fed8069b5f7d9240d46614390e637f2546adab964547c9e63a8f83
model-00029-of-00036.safetensors5.51 GBbcb63d72f9e6e16c7d154fae4ebd778f2aa1c4f6c68fb7900442502b05c154a3
model-00030-of-00036.safetensors5.51 GBc4d2fb84be1904e066672c7f85154cd845143c8c0b90671a887a14442a865e4c
model-00031-of-00036.safetensors5.51 GBb07faf0778035b49953276542e5733443c4a202c5c78b26b6f3b689d169852b7
model-00032-of-00036.safetensors5.51 GB884ffd347c3371f1a0a1b308ff002e0edeac990264244bb8e611aad25ad3722b
model-00033-of-00036.safetensors5.51 GBf4ae5a1a0272c5147e03905a49b885f155c0284d205d93505f8faba41f357a99
model-00034-of-00036.safetensors5.51 GBae9076d271e3f0ac76c5eabdc8e1f70b27c57009238487b1b5727a01e6ab3f2d
model-00035-of-00036.safetensors5.51 GBac21e5d6b074a73cd45117ac61416d186bad6a9c7a8d7d6b1f5625d94b05b1a5
model-00036-of-00036.safetensors3.43 GB7491c61a2069a4dfd018ced07cd34b2217d79d9abc16c62d9ece6591c475f7e1
model.safetensors.index.json405 KBf9e4ba2c0833ec2cf917a352fc1bbf1bec894c357c7721295e301aed02bea6d8
preprocessor_config.json390 B27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
processor_config.json991 B45fc17c8dd2474af6b493b52483c26c0584b0082d368c480f9fa611e73070040
tokenizer.json20.0 MB06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
tokenizer_config.json1.17 KB792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b
vocab.json6.72 MBce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
2a9de02543 pinned now2026-11-15 05:07 UTC50 files · 195 GB

Use it

# custom terms: read the license before you download
$ fw get mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp
# manifest sha256 17906d2062a3… · 195 GB · 50 files
$ fw verify ./Qwen3.8-Flash-Next-oQ8e-mtp mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp
Custom license (custom). Read the license text first. Open this panel to show the commands once you accept its terms.
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp.json --dir ./Qwen3.8-Flash-Next-oQ8e-mtp $ python3 fw.py verify ./Qwen3.8-Flash-Next-oQ8e-mtp ./mlx-community__Qwen3.8-Flash-Next-oQ8e-mtp.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp --revision 2a9de025436ea977720e4e3d6f369b185838e791 --local-dir ./Qwen3.8-Flash-Next-oQ8e-mtp

License

Name
LicenseRef-Qwen-Community-1.0
Id
LicenseRef-Qwen-Community-1.0
Class
Custom terms
Redistribution
click-through
Listing
Hosted (signed)
Decided
Same license text as one a person already read. 2026-11-15
Text in
LICENSE
Text sha256
a0dc422560841fd68e06d974907f8b4c709bca44a67daad2b528437bdf676c08
Terms gate
Yes. The commands stay folded until you open them after reading 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.qwenSubject: Qwen3.8-Flash-Next-oQ8e-mtpDate: 2026-11-15Commit: 2a9de02Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp
Pinned commit
2a9de025436ea977720e4e3d6f369b185838e791
Manifest
Qwen3.8-Flash-Next-oQ8e-mtp.json · .minisig
Manifest sha256
17906d2062a3ecd7d1487b084029e069edf7f2dbbff2f626c70e46a4162a977b
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:07 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp.json.minisig $ minisign -Vm Qwen3.8-Flash-Next-oQ8e-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

Qwen/Qwen3.8-Flash-Next · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Read license, then download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3.8-Flash-Next-oQ8e-mtp.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3.8-Flash-Next-oQ8e-mtp

Related models

All of alt.freeweights.qwen →
From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF