qwen3.5-397b-gguf-q6k-llama-cpp

llama-cpprpc@sparkrun-transitional

Qwen3.5 397B (GGUF, unsloth quant, Q6_K)

Quick Info

Runtimellama-cpp (rpc)

Tensor Parallel1

Nodes4+

Parameters397B

Dtypeq6_k

Containerscitrera/dgx-spark-llama-cpp:b8192-cu131

Tensor Parallel (--tp)GPU Memory (--gpu-mem)Port (--port)Served Model Name

sparkrun run @sparkrun-transitional/qwen3.5-397b-gguf-q6k-llama-cpp