alt.freeweights.text / Flint-GGUF

From:

ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.textSubject:

Flint-GGUF

Date: 2026-11-15Commit: b676335Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 145 GB in all. Published by ggml-org under Apache-2.0.

text

145GBFlint-GGUFggufpermissive

FactsParamsnot statedSize145 GBFormatsggufTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get ggml-org/Flint-GGUF
# manifest sha256 5dba2d40c312… · 145 GB · 7 files
$ fw verify ./Flint-GGUF ggml-org/Flint-GGUF

From sourceHosted (signed)ggml-org/Flint-GGUFLast check: 2026-11-15 04:39 UTC

Run at home Get help

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

Quantized of flint.

Works with

Run14 Convert1 Evaluate13 Scan12 Apps58

Runs with

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

Text Generation WebUI mistral.rs

Ollama

llama.cpp LocalAI

BitNet llamafile gpu-unlock KoboldCpp PocketPal AI llama-swap ik_llama.cpp

Show all 14

RamaLama Maid

Convert with

ggml

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 145 GB
Weights: 23.4 GB (smallest of 3 GGUF variants)
Parameters: not stated
Formats: gguf
Task: text generation
License: Apache-2.0 (permissive)
Files: 7, each with a sha256
Publisher: ggml-org
Added: 2026-11-15
Section: alt.freeweights.text

Lineage

Original release from the publisher.

Base model: RecursiveSI/flint

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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 04:39 UTC	passed

Model card

From the publisher at commit b676335. Shown as plain text with links; images open at the publisher.

Flint#

Run it in the Llama app: https://llama.app

Or from the terminal:

llama serve -hf ggml-org/Flint-GGUF

Source models#

https://huggingface.co/RecursiveSI/flint

Notes#

Ships BF16, Q8_0 and Q4_K_M.
39.8B MoE (~2.5B active), 49 layers (2 dense + 47 MoE), 256 routed experts with 6 active per token plus a shared expert, 262K context.
In Q4_K_M the small non-expert tensors (embeddings, attention, shared expert) are kept at Q8_0.
Text-only source: no mmproj, MTP or DFlash sidecars.
Requires a llama.cpp build with Flint support: https://github.com/ggml-org/llama.cpp/pull/30928

Important. This model is automatically converted using https://github.com/ggml-org/convert

Files

7 files · 145 GBWeights 23.4 GB (smallest of 3 GGUF variants). Sizes and sha256 from the signed manifest.

Hide all 7 files with their sha256

File	Size	sha256
.gitattributes	1.68 KB	f483f7fe4912167dbd4aabb6725a5c4cd64cb5203367b457a6f0b9b8734e2382
.src_sha	49 B	0c7148de70c583390af599346eaf349025f59f8c8d0e3083a694ccc0c4c26442
Flint-BF16.gguf	79.6 GB	bddf310fc9f33ad394674a6d94f1ba3fe4d83c0ad57bb69f72cc0d443146ff2e
Flint-Q4_K_M.gguf	23.4 GB	c3c4d93f9db92627a2fc47ea8fe8c64a094cabd3549db544bcdd2c00e9a9a347
Flint-Q8_0.gguf	42.4 GB	8a257b63c0fd1611947db267e3fa84ac3de0ed6f4c43255612236afd226a4f93
README.md	838 B	157606bb0c670d4346a0c61889bc421d5f159a664a3ebe8ea50dc713ac42f030
convert.log	358 KB	52dd468ddef1edec533e5b699e1749443a642ca3b36a670d1aed66a1da7ccdd8

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
b6763353f6 pinned now	2026-11-15 04:39 UTC	7 files · 145 GB

Use it

$ fw get ggml-org/Flint-GGUF
# manifest sha256 5dba2d40c312… · 145 GB · 7 files
$ fw verify ./Flint-GGUF ggml-org/Flint-GGUF

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/ggml-org/Flint-GGUF.json --dir ./Flint-GGUF
$ python3 fw.py verify ./Flint-GGUF ./ggml-org__Flint-GGUF.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/Flint-GGUF --revision b6763353f6f47bb4ae94f9f57d2d36906d2e4543 --local-dir ./Flint-GGUF

llama.cppDownload one GGUF variant (Flint-Q4_K_M, 23.4 GB), then serve it.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/Flint-GGUF --include "Flint-Q4_K_M*" --local-dir ./Flint-GGUF
$ llama-server -m ./Flint-GGUF/Flint-Q4_K_M.gguf

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./Flint-GGUF/Flint-Q4_K_M.gguf\n' > Modelfile
$ ollama create flint-gguf -f Modelfile

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: 157606bb0c670d4346a0c61889bc421d5f159a664a3ebe8ea50dc713ac42f030
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:

ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.textSubject: Flint-GGUFDate: 2026-11-15Commit: b676335Signed: 2DC28CC7B26A283B ✓

Upstream: ggml-org/Flint-GGUF
Pinned commit: b6763353f6f47bb4ae94f9f57d2d36906d2e4543
Manifest: Flint-GGUF.json · .minisig
Manifest sha256: 5dba2d40c3121b1f3886f4d35ea63189dda2b0852ce8a9b6b998619e0db43f4e
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 04:39 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/Flint-GGUF.json
$ curl -O https://freeweights.allternit.com/manifests/ggml-org/Flint-GGUF.json.minisig
$ minisign -Vm Flint-GGUF.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

RecursiveSI/flint · 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 ggml-org/Flint-GGUF

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. Flint-GGUF.json. Provenance. Takedown history: none.

Source

huggingface.co/ggml-org/Flint-GGUF

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