Downloads · 30 days
266
46% of all-time downloads
jnjn/Ornith-1.5-35B-A3B-Spark-Abliterated-VL-MTP-NVFP4
Ornith-1.5-35B-A3B-Spark-Abliterated-VL-MTP-NVFP4 is a image-text-to-text model from jnjn. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This model provides a vLLM recipe that runs on DGX spark and similar powered machines (Blackwell+ with ~44GB+ VRAM) with an Abliterated Ornith 1.5 35B which has Vision Tower and MTP, in NVFP4.
Downloads · 30 days
266
46% of all-time downloads
All-time downloads
574
Public
Parameters
36B
24.2 GB on disk
Likes
3
Public
Click a slice to open those files.
.safetensors24.2 GB · 100%
How the weights are stored.
U832.8B · 91%
From the Hugging Face model README
This model provides a vLLM recipe that runs on DGX spark and similar powered machines (Blackwell+ with ~44GB+ VRAM) with an Abliterated Ornith 1.5 35B which has Vision Tower and MTP, in NVFP4.
Merged model:
pottokao/Ornith-1.5-35B-A3B-abliterated-NVFP4-DFlash (abliterated), renamed model.* -> model.language_model.*ornith-ai/Ornith-1.5-35B-A3B-NVFP4 (model.visual.*, 333 tensors)ornith-ai/Ornith-1.5-35B-A3B-NVFP4 (mtp.*, 785 tensors, unquantized per quantization_config.ignore)ornith-ai (multimodal Qwen3_5MoeForConditionalGeneration)pottokao under dflash_draft/ for optional --speculative-config method=dflashTotal tensors: 94393 (same layout as ornith-ai, 3 shards).
OMP_NUM_THREADS=4 MAX_JOBS=4 vllm serve \
jnjn/Ornith-1.5-35B-A3B-Spark-Abliterated-VL-MTP-NVFP4 \
--load-format fastsafetensors \
--port 8000 \
--tool-call-parser qwen3_coder \
--reasoning-parser qwen3 \
--enable-auto-tool-choice \
--served-model-name ornith-1.5-35b-a3b ornith qwen-3.x-moe qwen3 qwen \
--gpu_memory_utilization 0.45 \
--max_model_len 262144 \
--max-num-seqs 32 \
--max-num-batched-tokens 8192 \
--trust-remote-code \
--async-scheduling \
--mamba-cache-mode align \
--mamba-block-size 8 \
--enable-prefix-caching \
--speculative-config '{"method":"mtp","num_speculative_tokens":3}'