From: unsloth <huggingface.co/unsloth> Newsgroups: alt.freeweights.gemmaSubject: gemma-2b-bnb-4bit Date: 2026-11-15Commit: ee801bdSigned: 2DC28CC7B26A283B ✓ Text generation model with 2.6B parameters. Safetensors weights, 2.09 GB in all. Published by unsloth under Apache-2.0.
2.6B params 2.09 GB gemma-2b-bnb-4bit safetensors permissive Facts Params 2.6B Size 2.09 GB Formats safetensors Task text generation License Apache-2.0 From sourcepermissive
fw
$ fw get unsloth/gemma-2b-bnb-4bit
# manifest sha256 25daa8a88116… · 2.09 GB · 9 files
$ fw verify ./gemma-2b-bnb-4bit unsloth/gemma-2b-bnb-4bit
From sourceHosted (signed) unsloth/gemma-2b-bnb-4bit Last check: 2026-11-15 03:39 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 2.09 GB
Weights 2.07 GB (safetensors)
Parameters 2.6B
Formats safetensors
Task text generation
License Apache-2.0 (permissive)
Files 9, each with a sha256
Publisher unsloth
Added 2026-11-15
Section alt.freeweights.gemma
Lineage
Original release from the publisher.
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 sourcehuggingface.co 2026-11-15 03:39 UTC passed
Model card From the publisher at commit
ee801bd . Shown as plain text with links; images open at the publisher.
Files 9 files · 2.09 GB Weights 2.07 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 9 files with their sha256 File Size sha256 .gitattributes 1.57 KB 34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930 README.md 3.08 KB 613705690927e70e626ac7895e3a8e24da098fcd9804b32b0fe7175829f7ebb9 config.json 1.20 KB e3c27e6614f0e874226acea92ab356ea7dfd33848649d5fb09904b25e6c2fb51 generation_config.json 154 B 4358ba9459393634465be72b3428013c0e946aef4c18f50f26f94443070d3f8a model.safetensors 2.07 GB 6e6a85312f388d3b68896adda2508de66821d169526e262d6bd0525ab350c603 special_tokens_map.json 636 B baec30ea10906f16adb8c18af7a34023002c1746542612b8b41c9f09e1351351 tokenizer.json 17.5 MB 7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79 tokenizer.model 4.24 MB 61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 tokenizer_config.json 40.0 KB a9c97d9a9e90e0f3ef7db379ad2786e030830de8d27e4d474408b44b52c1a624
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents ee801bdc94 pinned now 2026-11-15 03:39 UTC 9 files · 2.09 GB
Use it fw
$ fw get unsloth/gemma-2b-bnb-4bit
# manifest sha256 25daa8a88116… · 2.09 GB · 9 files
$ fw verify ./gemma-2b-bnb-4bit unsloth/gemma-2b-bnb-4bitfw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/unsloth/gemma-2b-bnb-4bit.json --dir ./gemma-2b-bnb-4bit
$ python3 fw.py verify ./gemma-2b-bnb-4bit ./unsloth__gemma-2b-bnb-4bit.json Copyhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download unsloth/gemma-2b-bnb-4bit --revision ee801bdc9451d4427d251f6377f5df1f67785e19 --local-dir ./gemma-2b-bnb-4bit Copytransformers Load the weights in Python.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("unsloth/gemma-2b-bnb-4bit", revision="ee801bdc9451d4427d251f6377f5df1f67785e19")
model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-2b-bnb-4bit", revision="ee801bdc9451d4427d251f6377f5df1f67785e19", device_map="auto") CopyvLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve unsloth/gemma-2b-bnb-4bit --revision ee801bdc9451d4427d251f6377f5df1f67785e19 CopyLicense 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 613705690927e70e626ac7895e3a8e24da098fcd9804b32b0fe7175829f7ebb9 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: unsloth <huggingface.co/unsloth> Newsgroups: alt.freeweights.gemmaSubject: gemma-2b-bnb-4bit Date: 2026-11-15Commit: ee801bdSigned: 2DC28CC7B26A283B ✓ Upstream unsloth/gemma-2b-bnb-4bit Pinned commit ee801bdc9451d4427d251f6377f5df1f67785e19 Manifest gemma-2b-bnb-4bit.json · .minisig Manifest sha256 25daa8a881165adf61620169985a7b3d2d2c4ffe07c84fd356593de71eda046e Signature minisign, Ed25519, key 2DC28CC7B26A283B Created 2026-11-15 03:39 UTC Generator freeweights-manifest/0.1.0 Takedowns None.
How to verify
$ curl -O https://freeweights.allternit.com/manifests/unsloth/gemma-2b-bnb-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/unsloth/gemma-2b-bnb-4bit.json.minisig
$ minisign -Vm gemma-2b-bnb-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file> # compare with the Files tab Copy
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 No related models in this catalog. Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT =https://freeweights.allternit.com hf download unsloth/gemma-2b-bnb-4bit Copy
Open in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
gemma 2.17 GB Alexandria-Gemma-4-12B-it-Ornith9-Summaries-LoRA-r128 safetensors permissive Facts Params not stated Size 2.17 GB Formats safetensors Task text generation License CC-BY-4.0 From sourcepermissive flip From: laion <huggingface.co/laion> Subject: Alexandria-Gemma-4-12B-it-Ornith9-Summaries-LoRA-r128 gemma 1.13 GB Alexandria-Gemma-4-12B-it-Ornith9-Summaries-LoRA-r64 safetensors permissive Facts Params not stated Size 1.13 GB Formats safetensors Task text generation License CC-BY-4.0 From sourcepermissive flip From: laion <huggingface.co/laion> Subject: Alexandria-Gemma-4-12B-it-Ornith9-Summaries-LoRA-r64 gemma 2.14 GB Alexandria-Gemma-4-12B-it-Qwen27-Knowledge-Units-LoRA-r128 safetensors permissive Facts Params not stated Size 2.14 GB Formats safetensors Task text generation License CC-BY-4.0 From sourcepermissive flip From: laion <huggingface.co/laion> Subject: Alexandria-Gemma-4-12B-it-Qwen27-Knowledge-Units-LoRA-r128 gemma 2.17 GB Alexandria-Gemma-4-12B-it-Qwen27-Summaries-LoRA-r128 safetensors permissive Facts Params not stated Size 2.17 GB Formats safetensors Task text generation License CC-BY-4.0 From sourcepermissive flip From: laion <huggingface.co/laion> Subject: Alexandria-Gemma-4-12B-it-Qwen27-Summaries-LoRA-r128 gemma 1.12 GB Alexandria-Gemma-4-12B-it-Qwen27-Summaries-LoRA-r64 safetensors permissive Facts Params not stated Size 1.12 GB Formats safetensors Task text generation License CC-BY-4.0 From sourcepermissive flip From: laion <huggingface.co/laion> Subject: Alexandria-Gemma-4-12B-it-Qwen27-Summaries-LoRA-r64 gemma 1.15 GB Alexandria-Gemma-4-E4B-it-Qwen27-Knowledge-Units-LoRA-r128 safetensors permissive Facts Params not stated Size 1.15 GB Formats safetensors Task text generation License CC-BY-4.0 From sourcepermissive flip From: laion <huggingface.co/laion> Subject: Alexandria-Gemma-4-E4B-it-Qwen27-Knowledge-Units-LoRA-r128