跳转到主要内容

AI models that run on this device.

Two small chat models run in a computer’s browser here; every other model is a file you download.

RedHatAI

phi-4-quantized.w8a8

Can I run phi-4-quantized.w8a8 on my computer?

It depends on your memory, processor, file format and runtime. Hugging Bay offers 10 hosted files; check the file list for the exact selection. A file-size fit is an estimate, not a successful run or speed promise. Read the license before use.

phi-4-quantized.w8a8 is an open-weights language model for text generation. Model weights are learned parameters; a runtime loads them. A hosted file is an individual file Hugging Bay can serve. SHA-256 identifies exact file bytes. The availability date above applies to this file record, not the upstream metadata update date.

As of the recorded file availability check on .

Recorded SHA-256 for model-00001-of-00004.safetensors: f23d33263467eed121cb223009b19dfacf657fa3f17383d8b6c5302b3403338e. Exact file evidence · Machine-readable source facts · Run evidence and any recorded receipts. A checksum fingerprints only the named file bytes; it does not prove safety, quality, a complete multi-file selection or a successful run.

Updated · Page-copy source revision 8871bab84e1cf80aea1686a944ec335078a6c036 · Source files: apps/web/lib/model-page-template.mjs, apps/web/lib/model-page-v3.mjs, apps/web/lib/aeo-page.mjs · Full revision record

Model metadata: As of at the model source. Popularity counters are source-reported, not measured by Hugging Bay. Availability checked .

Try browser chat with a small demo model (a separate model; device support is checked before loading).

RedHatAI/phi-4-quantized.w8a8
Model details
text generationLicense: mitSHA-256 recorded for 10 of 15 filessafetensors

Content controls: not assessed.

The catalog lists this model for working with code. Catalog sources: license, cardMetadata.license, tags, task, cardMetadata.pipelineTag.

10 hosted of 15 listed

Hashes recorded. Date not recorded.

File大小SHA-256来源下载
Weights
model-00001-of-00004.safetensors4.84 GB
f23d3326…3403338ef23d33263467eed121cb223009b19dfacf657fa3f17383d8b6c5302b3403338e
Hosted下载
model-00002-of-00004.safetensors4.96 GB
077a5654…6de173a6077a5654b53a65595f614c158735abf4d20420d310e93241f485f7946de173a6
Hosted下载
model-00003-of-00004.safetensors4.86 GB
aacbc16c…183b8ef3aacbc16c7e525c3166a12307c1061a1885e6710b1b7eff07c36349f0183b8ef3
Hosted下载
model-00004-of-00004.safetensors1.03 GB
5839c81a…68e7c1f35839c81af91221e4d409b7fac2c3e7d348774887a39841e184ac73bc68e7c1f3
Hosted下载
Tokenizer & config
config.json1.9 KB
655a836d…be37d00b655a836d93b198a2d2a5d65662a2ff65988ef142b5cea1287adbd935be37d00b
Hosted下载
generation_config.json147 bytes
7397474c…b94e591c7397474c28540baff3533db982933e9516916bd02088faff2297bfafb94e591c
Hosted下载
merges.txt916.6 KB—Upstream onlyFile metadata
model.safetensors.index.json34.5 KB
72664619…efb6d563726646193ae6e3a9d133d1385338bafb81cd73a53c50168fa676063eefb6d563
Hosted下载
recipe.yaml616 bytes—Upstream onlyFile metadata
special_tokens_map.json463 bytes
beb064d7…3f6c0c42beb064d75e46a606ef1404691efc14c40b73b98ba4e4b20f35f1383b3f6c0c42
Hosted下载
tokenizer.json7.15 MB
c612e57b…391c9884c612e57b2763204798271c0cdc14a373a565e6a371f1bfbd44e385a8391c9884
Hosted下载
tokenizer_config.json17.8 KB
4876c749…6033c9c64876c7490dd953d2666509be3720355d3a488e76347a111958b020626033c9c6
Hosted下载
vocab.json1.61 MB—Upstream onlyFile metadata
Docs
.gitattributes1.52 KB—Upstream onlyFile metadata
README.md12.8 KB—Upstream onlyFile metadata

检查下载文件

In the folder where you saved config.json, run:

macOS
shasum -a 256 -- 'config.json'
Linux
sha256sum -- 'config.json'
Windows
Get-FileHash -LiteralPath 'config.json' -Algorithm SHA256

Compare the result with the recorded SHA-256.

类似的托管模型

浏览托管模型