inclusionAI/Ling-3.0-tiny-GGUF

Source: 🤗At risk🏴‍☠️ Rescued by: Sherpatext-generationmit41 GBGGUF✓ 5 checksumsupdated 65d ago

🧲 Magnet🌱 0

🤗 Hugging Face | 🤖 ModelScope | 🐙 OpenRouter

Ling-3.0-tiny-GGUF

Ling-3.0-tiny is a lightweight hybrid reasoning MoE model with 7.9B total parameters and only 1.3B activated parameters per token. It is designed to deliver strong reasoning and agentic capabilities at low inference cost, making advanced model capabilities more accessible for local and resource-constrained deployment.

Find more details in the original model card: https://huggingface.co/inclusionAI/Ling-3.0-tiny

CommentsShare your thoughts and shape the future of sovereign AI.

@inclusionAI is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @inclusionAI

Files and sources

✓SourceAvailable on Hugging Face

✓Checksums5 recorded

✓TorrentMagnet listed

4Swarm0 seeders reported

Source revision: 01b850e29ed5…
Witnessed: 23 Sept 2026, 13:51 UTC
Swarm checked: 4 Nov 2026, 10:33 UTC
Weight files: 5
Model size: 41 GB
Downloads · last month: 13,872
Publisher: Unclaimed

Speed on real hardware

LocalMaxxing

Output speed for one request at a time, measured by people running this model on their own machines.

RTX 5070llama.cpp · Q8_0 · 1 run244 tok/s
```
llama-bench -m Ling-3.0-tiny-Q8_0.gguf -p 512 -n 128 -ngl 99 -fa 1
```
View run on LocalMaxxing

Median of 1 community runs on 1 setups, from LocalMaxxing.

Run it yourself: setup guide →

View provenance entry #8792 →

Speed on real hardware

LocalMaxxing

Output speed for one request at a time, measured by people running this model on their own machines.

RTX 5070llama.cpp · Q8_0 · 1 run244 tok/s
```
llama-bench -m Ling-3.0-tiny-Q8_0.gguf -p 512 -n 128 -ngl 99 -fa 1
```
View run on LocalMaxxing

Median of 1 community runs on 1 setups, from LocalMaxxing.

Run it yourself: setup guide →