cmh/Jan-v2-VL-max-Instruct-FP8-GGUF

Partial fine-tune vs Qwen/Qwen3-VL-30B-A3B-Instruct. cmh/Jan-v2-VL-max-Instruct-FP8-GGUF is a GGUF (F16) of different weights. Partial change: 60% of the weights changed (attention, mlp, norms), in 48 of 48 layers.

Tensors changed: Embeddings 0/1, Norms 52/193, MLP 48/48, Attention 192/192, lm_head 0/1

On the Hub · Downloads on Model Pulse