Downloads · 30 days
1
7% of all-time downloads
Lucierr8732/Qwen3-1.7B-LOMO-q4f16_1-MLC2
Qwen3-1.7B-LOMO-q4f16_1-MLC2 is a text generation model from Lucierr8732. Use it when you need the model to write or continue text. It is set up for mlc-llm. The card lists the license as other.
MLC-LLM formatted weights for on-device inference (Android / Vulkan, CPU, etc.).
Downloads · 30 days
1
7% of all-time downloads
All-time downloads
15
Public
Repo size
979 MB
Likes
0
Public
Click a slice to open those files.
.bin968 MB · 98%
From the Hugging Face model README
MLC-LLM formatted weights for on-device inference (Android / Vulkan, CPU, etc.).
Qwen/Qwen3-1.7Bq4f16_1 (group size 32, int4 weights + f16 scales)chatml ← match runtime prompt formatting with trainingmlc-chat-config.jsonparams_shard_*.bintensor-cache.jsontokenizer.json + vocab.json + merges.txt)mlc_llm chat HF://raining-codes/Qwen3-1.7B-LOMO-q4f16_1-MLC2 --temperature 0.7 --top-p 0.9 --max-gen-len 256
raining-codes/Qwen3-1.7B-LOMO-q4f16_1-MLC2.