dicksondickson/Swift-1.5-Qwen3.8-27b-oQ5e-fp16-mtp

Source: 🤗At risk🏴‍☠️ Rescued by: Sherpamit27.8B params56 GBsafetensors✓ 6 checksumsupdated 36d ago

🧲 Magnet🌱 0

dicksondickson/Swift-1.5-Qwen3.8-27b-oQ5e-fp16-mtp

This model is a quantization of: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b

This checkpoint was quantized using oMLX 0.7.0rc1 with imatrix enabled.

FP16 is for M1/M2 chips. For M3/M4/M5 use the BF16 variant:
https://huggingface.co/dicksondickson/Swift-1.5-Qwen3.8-27b-oQ5e-bf16-mtp-MLX

Run the model using oMLX: https://github.com/jundot/omlx

CommentsShare your thoughts and shape the future of sovereign AI.

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

Files and sources

✓SourceAvailable on Hugging Face

✓Checksums6 recorded

✓TorrentFiles match Hugging Face

4Swarm0 seeders reported

Source revision: 999f295f55af…
Witnessed: 3 Oct 2026, 20:29 UTC
Swarm checked: 4 Nov 2026, 22:09 UTC
Weight files: 6
Model size: 56 GB
Downloads · last month: 796
Publisher: Unclaimed

View provenance entry #21198 →