Hugging Face's logo

hipfire-models
/
qwen3.5-9b-dev

English
hipfire
quantization
lloyd-max
research
qwen3.5
Model card Files
xet
 Community
qwen3.5-9b-dev

Commit History

  1. Delete qwen3.5-9b.mq4-awq-gptq-q8conv-f2-cuda.hfq

    kread
    Verified signature
    2d42fd9

  2. Rename qwen3.5-9b.mq4-awq-gptq-f2-lmhead-a100.hfq to qwen3.5-9b.mq4

    kread
    Verified signature
    69611ba

  3. Add qwen3.5-9b-vl.mq4 (awq-gptq f2 lmhead a100-vl)⁠

    kread
    Verified signature
    cb2caf5

  1. Add qwen3.5-9b.mq4-awq-gptq-f2-lmhead-a100.hfq (AWQ+GPTQ MQ4 with AWQ-on-lm_head, A100-built)

    kread
    Verified signature
    50d95d2

  1. Add Qwen3.5-9B MQ4 AWQ-GPTQ Q8conv F2 (CUDA path, alpha=0.55)

    kread
    Verified signature
    2a5782d

  1. Add qwen3.5-9b.mq4-lloyd (Phase B WMMA prefill research quant, PR #197)

    kread
    Verified signature
    a1a1b6a

  2. Add qwen3.5-9b.mq3-lloyd

    kread
    Verified signature
    768054c

  3. Initial: research-gated MQ3-Lloyd + MQ4-Lloyd disclaimer

    kread
    Verified signature
    417df48

  4. initial commit

    kread
    Verified signature
    875d092