vvsotnikov/Qwen3.8-27B-MTP-MLX-4bit
Text Generation • 0.4B • Updated • 730
Edit Models filters
Model Tree
Apps
Inference Providers
One-click Deployment
Models
672
Active filters: draft-model
vvsotnikov/Qwen3.8-27B-MTP-MLX-bf16
Text Generation • 0.4B • Updated • 1.68k • 2
vvsotnikov/Qwen3.8-27B-MTP-MLX-8bit
Text Generation • 0.4B • Updated • 602
TaterTotterson/Qwen3.8-27B-GGUF-Tater-NoThink
Image-Text-to-Text • 27B • Updated • 1.67k • 1
inferencerlabs/Qwen3.8-27B-MTP-MLX
Image-Text-to-Text • 0.4B • Updated • 1.54k • 1
efficiencyx/Jun-LoRA-12B-MTP-GGUF
0.4B • Updated • 75
mlx-community/Qwen3.8-27B-MTP-mxfp4
Text Generation • 0.4B • Updated • 2.35k
mlx-community/Qwen3.8-27B-MTP-mxfp8
Text Generation • 0.4B • Updated • 4.98k • 6
mlx-community/Qwen3.8-27B-MTP-nvfp4
Text Generation • 0.4B • Updated • 3.16k • 1
lukaskremla/Qwen3.8-27B-MTP-bf16-MLX
Text Generation • 0.4B • Updated • 976 • 1
erlidev/Qwen3.8-27B-DSpark-GGUF
Text Generation • 1B • Updated • 4.34k • 3
lukaskremla/Qwen3.8-27B-MTP-8bit-MLX
Text Generation • 0.4B • Updated • 389
lukaskremla/Qwen3.8-27B-MTP-6bit-MLX
Text Generation • 0.4B • Updated • 553
lukaskremla/Qwen3.8-27B-MTP-5bit-MLX
Text Generation • 0.4B • Updated • 358
lukaskremla/Qwen3.8-27B-MTP-4bit-MLX
Text Generation • 0.4B • Updated • 455
lukaskremla/Qwen3.8-27B-MTP-2bit-MLX
Text Generation • 0.4B • Updated • 1.07k • 1
him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S
20B • Updated • 264
D4pp3rD1scourse/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-DFlash
0.8B • Updated • 1.33k
Lynxpda/DeepSeek-V4-Flash-0731-DSpark-Drafter-Q2_K_S-GGUF
20B • Updated • 858 • 1
DimInfer/Qwen3.8-27B-Dspark-v1
2B • Updated • 11.9k • 10
kirikir13/gemma-4-E4B-it-qat-assistant-bf16
Text Generation • 78.8M • Updated • 412
julyanghar/Efficient-DRAgent
0.7B • Updated • 11
Unkto/DeepSeek-V4-Flash-0731-DSpark-Drafter-IQ1M-IQ2XXS-GGUF
20B • Updated • 2.2k • 2
VisualInference/Qwen3.8-27B-AEON-Ultimate-Uncensored-MLX-MTP-Drafter
0.4B • Updated • 1.68k
kstoyanov99/Qwen3.8-27B-Dflash
2B • Updated • 1.26k • 2
xkm/qwen3.8-27b-mtp-head-retrained
0.4B • Updated
huluhuluu/Qwen3-4B-Instruct-2507-EAGLE3-ShareGPT-epoch-0-step-5000
0.2B • Updated • 16
huluhuluu/Qwen3-4B-Instruct-2507-EAGLE3-ShareGPT-epoch-0-step-10000
0.2B • Updated • 10
huluhuluu/Qwen3-4B-Instruct-2507-EAGLE3-ShareGPT-epoch-0-step-15000
0.2B • Updated • 11
huluhuluu/Qwen3-4B-Instruct-2507-EAGLE3-ShareGPT-epoch-0-step-20000
0.2B • Updated • 8