> I'd love to load this up on the old 2080ti with 128gb of vram and play, even slowly.
I think you mean ram and no vram. AFAIK this is a 30b moe model with 3b active parameters. Comparable to the Qwen3 MOE model. If you do not expect 60 tps such models should run sufficiently fast.
I run the Qwen3 MOE Model (https://huggingface.co/unsloth/Qwen3-30B-A3B-GGUF/blob/main/...) in 4-bit quantization on an 11 year old i5-6600 (32GB) and a Radeon 6600 with 8GB. According to a quick search your card is faster than that and I get ~12 tps with 16k context on Llama.cpp, which is ok for playing around.
My Radeon (ROCm) specific batch file to start this:
FWIW Ollama at its defaults with qwen3:30b-a3b has 256k context size and does ~27 tokens/sec on pure CPU on a $450 mini PC with AMD Ryzen 9 8945HS. Unless you need a room heater, that GPU isn't pulling its weight.
I think you mean ram and no vram. AFAIK this is a 30b moe model with 3b active parameters. Comparable to the Qwen3 MOE model. If you do not expect 60 tps such models should run sufficiently fast.
I run the Qwen3 MOE Model (https://huggingface.co/unsloth/Qwen3-30B-A3B-GGUF/blob/main/...) in 4-bit quantization on an 11 year old i5-6600 (32GB) and a Radeon 6600 with 8GB. According to a quick search your card is faster than that and I get ~12 tps with 16k context on Llama.cpp, which is ok for playing around.
My Radeon (ROCm) specific batch file to start this:
llama-server --ctx-size 16384 --flash-attn on --cache-type-k q8_0 --cache-type-v q8_0 --device ROCm0 -ngl -1 --model /usr/local/share/gguf/Qwen3-30B-A3B-Q4_0.gguf --cache-ram 16384 --cpu-moe --numa distribute --override-tensor "\.ffn_.*_exps\.weight=CPU" --jinja --temp 0.7 --port 8080