weareapexcreators/Qwen3.5-2B-MTP-LocalAI

Source: 🤗🏴‍☠️ Rescued by: Alogotronapache-2.02B activated3.5 GBGGUF✓ 4 checksumsupdated 141d ago

🧲 Magnet🌱 4

No README published on Hugging Face for this revision.

Loading…

CommentsShare your thoughts and shape the future of sovereign AI.

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

Files and sources

✓SourceAvailable on 🤗

✓Checksums4 recorded

✓TorrentMagnet listed

✓Swarm4 seeders reported

Source revision: 849c9cf196f4…
Witnessed: 14 Oct 2026, 06:27 UTC
Swarm checked: 15 Nov 2026, 20:11 UTC
Weight files: 4
Model size: 3.5 GB
Downloads · last month: 18,931
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.

2× RTX 3090llama.cpp · Q4_K_M · 1 run343 tok/s

LD_LIBRARY_PATH=/home/beta1/qwen38-release/tools/llama-b10442-cuda /home/beta1/qwen38-release/tools/llama-b10442-cuda/llama-bench -m /mnt/pf/pf-deep2/Qwen3.5-2B-MTP-LocalAI/Qwen3.5-2B-Q4_K_M.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 #29659 →