Can the RTX 6000D run Llama 3.3 70B?

Yes. Llama 3.3 70B fits the RTX 6000D's 84 GB at Q4_K_M (about 41.8 GB needed), running at an estimated 23 tok/s. There's room for up to Q8_0 if you want higher quality.

VRAM

84 GB

Needs at Q4

41.8 GB

Headroom

42.2 GB

Speed (Q4_K_M)

~23 tok/s

Every quantization

Llama 3.3 70B (70B) on 84 GB

Quant	Weights	Needs	Fit	Est. speed
Q4_K_M	40 GB	41.8 GB	Fits easily	~23 tok/s
Q5_K_M	48 GB	49.8 GB	Fits easily	~19 tok/s
Q8_0	75 GB	76.8 GB	Tight	~12 tok/s
FP16	140 GB	141.8 GB	Too big	-

Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 6000D's 1570 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.

Run it

Copy, paste, go

ollama run llama3.3:70b

llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF -ngl 99

Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Llama 3.3 70B details →

Compare

Same model, other hardware - and other models on this card

Llama 3.3 70B on other hardware

Also runs on the RTX 6000D

RTX 6000D specs →Everything the RTX 6000D can run →

Frequently asked

Quick answers

Can the RTX 6000D run Llama 3.3 70B?

Yes. Llama 3.3 70B fits the RTX 6000D's 84 GB at Q4_K_M (about 41.8 GB needed), running at an estimated 23 tok/s. There's room for up to Q8_0 if you want higher quality.

How much VRAM does Llama 3.3 70B need?

About 40 GB of weights at Q4_K_M, 75 GB at Q8_0 and 140 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.

How fast is Llama 3.3 70B on the RTX 6000D?

Roughly 23 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 6000D's 1570 GB/s memory bandwidth.