Can I run Qwen3.8-35B-A3B-Distill on an RTX 6000 Ada?

Yes, with a GGUF version

The published weights are too big, but the Q8_0 file from empero-ai/Qwen3.8-35B-A3B-Distill-GGUF (37.8 GB) fits, with room for ≈ 254K tokens of context.

Full analysis of Qwen3.8-35B-A3B-Distill Everything that runs on RTX 6000 Ada Get the Q8_0 file on Hugging Face

ollama run hf.co/empero-ai/Qwen3.8-35B-A3B-Distill-GGUF:Q8_0

Files and context on RTX 6000 Ada

Each file of Qwen3.8-35B-A3B-Distill (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

File	Size	On RTX 6000 Ada	Context (16-bit)	Context (8-bit)
As published	71.9 GB	Doesn't fit	—	—
BF16empero-ai/Qwen3.8-35B-A3B-Distill-GGUF	71.1 GB	Doesn't fit	—	—
Q8_0empero-ai/Qwen3.8-35B-A3B-Distill-GGUF	37.8 GB	Tight	254K	256K
Q6_Kempero-ai/Qwen3.8-35B-A3B-Distill-GGUF	29.2 GB	Fits	256K	256K
Q5_K_Mempero-ai/Qwen3.8-35B-A3B-Distill-GGUF	25.3 GB	Fits	256K	256K
Q4_K_Mempero-ai/Qwen3.8-35B-A3B-Distill-GGUF	21.7 GB	Fits	256K	256K
IQ4_XSempero-ai/Qwen3.8-35B-A3B-Distill-GGUF	19.6 GB	Fits	256K	256K
Q3_K_Mempero-ai/Qwen3.8-35B-A3B-Distill-GGUF	17.7 GB	Fits	256K	256K
IQ3_Mempero-ai/Qwen3.8-35B-A3B-Distill-GGUF	16.3 GB	Fits	256K	256K
Q2_Kempero-ai/Qwen3.8-35B-A3B-Distill-GGUF	13.8 GB	Fits	256K	256K
IQ2_Mempero-ai/Qwen3.8-35B-A3B-Distill-GGUF	12.6 GB	Fits	256K	256K

Qwen3.8-35B-A3B-Distill on other hardware

Popular models that run on RTX 6000 Ada

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.