base_model:

• ornith-ai/Ornith-1.5-35B-A3B-NVFP4
• pottokao/Ornith-1.5-35B-A3B-abliterated-NVFP4-DFlash
  base_model_relation: merge
  license: mit
  language:
• en
  pipeline_tag: image-text-to-text
  tags:
• nvfp4
• 4bit
• Q4
• vision
• mtp
• moe
• qwen35_moe
• dflash
• vllm
• spark

Ornith-1.5-35B-A3B-Spark-Abliterated-VL-MTP-NVFP4

Merged model:

• Language core (LM + lm_head + embed + norm): from pottokao/Ornith-1.5-35B-A3B-abliterated-NVFP4-DFlash (abliterated), renamed model.* -> model.language_model.*
• Vision tower + merger: from ornith-ai/Ornith-1.5-35B-A3B-NVFP4 (model.visual.*, 333 tensors)
• MTP (multi-token prediction): from ornith-ai/Ornith-1.5-35B-A3B-NVFP4 (mtp.*, 785 tensors, unquantized per quantization_config.ignore)
• Config/tokenizer/processor: from ornith-ai (multimodal Qwen3_5MoeForConditionalGeneration)
• DFlash draft: preserved from pottokao under dflash_draft/ for optional --speculative-config method=dflash

Total tensors: 94393 (same layout as ornith-ai, 3 shards).

Use — tested on 1x DGX Spark, single-stream 70+ tok/s, 16-stream ~400 tok/s

OMP_NUM_THREADS=4 MAX_JOBS=4 vllm serve \
    jnjn/Ornith-1.5-35B-A3B-Spark-Abliterated-VL-MTP-NVFP4 \
    --safetensors-load-strategy eager \
    --port 8000 \
    --disable-custom-all-reduce \
    --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 pm2026 \
    --gpu_memory_utilization 0.65 \
    --max_model_len 262144 \
    --max-num-seqs 32 \
    --max-num-batched-tokens 16384 \
    --trust-remote-code \
    --async-scheduling \
    --mamba-cache-mode align \
    --mamba-block-size 8 \
    --enable-prefix-caching \
    --speculative-config '{"method":"mtp","num_speculative_tokens":3}'