Metis-1.6

Lernex 's Collections

Metis-1.6

Metis-1.6 Base

Metis-1.5

Metis-1.4

Metis-1.3

updated about 13 hours ago

Metis-1.6 post-trained reasoning and chat models (metis-chat/v1, <think> and direct modes, 131K context): Praxis (2.94B) and Logos (10.23B).

Upvote

Lernex/Metis-1.6-Praxis

Text Generation • 3B • Updated 2 days ago • 8

Note 2.94B (0.464B active/pass, 2 passes): BF16 reference, 6.16 GB
Lernex/Metis-1.6-Praxis-FP8

Text Generation • 3B • Updated 2 days ago

Note FP8 W8A8 for vLLM, SGLang and Dromos, 3.53 GB
Lernex/Metis-1.6-Praxis-NVFP4

Text Generation • 2B • Updated 2 days ago • 1

Note NVFP4 W4A16 for Dromos, 2.01 GB
Lernex/Metis-1.6-Logos

Text Generation • 10B • Updated 2 days ago • 13

Note 10.23B (1.18B active/pass, 2 passes): BF16 reference, 20.80 GB
Lernex/Metis-1.6-Logos-FP8

Text Generation • 10B • Updated 2 days ago

Note FP8 W8A8 for vLLM, SGLang and Dromos, 11.18 GB
Lernex/Metis-1.6-Logos-NVFP4

Text Generation • 6B • Updated 2 days ago • 1

Note NVFP4 W4A16 for Dromos, 6.57 GB
Lernex/Metis-1.6-Praxis-MLX-4bit

Text Generation • 3B • Updated about 14 hours ago

Note MLX 4-bit for Apple silicon, 2.0 GB
Lernex/Metis-1.6-Praxis-MLX-8bit

Text Generation • 3B • Updated about 14 hours ago

Note MLX 8-bit for Apple silicon, 3.2 GB
Lernex/Metis-1.6-Logos-MLX-4bit

Text Generation • 10B • Updated about 14 hours ago

Note MLX 4-bit for Apple silicon, 6.6 GB
Lernex/Metis-1.6-Logos-MLX-8bit

Text Generation • 10B • Updated about 14 hours ago

Note MLX 8-bit for Apple silicon, 11.1 GB
Lernex/Metis-1.6-Praxis-GGUF

Text Generation • 3B • Updated about 14 hours ago

Note GGUF for llama.cpp, BF16 to IQ4_XS, with the imatrix
Lernex/Metis-1.6-Logos-GGUF

Text Generation • 10B • Updated about 14 hours ago

Note GGUF for llama.cpp, BF16 to IQ4_XS, with the imatrix

Upvote