Yes — with 147.6 GB to spare
Llama 3.3 70B Instruct at Q4_K_M fits your Instinct MI300X entirely on the GPU at 8K context, at an estimated 81 tokens per second. There is room for its full 128K window.
Fully on GPU
8K context
Q4_K_M · 39.7 GB
Llama 3.3 Community
Released Dec 2024
Still the creative-writing favourite: consistent voice, takes direction. Needs 48 GB to sit comfortably on GPU at Q4.
The VRAM budget
weights 39.7 GB
Weights 39.7 GB
KV cache @ 8K 2.50 GB
Runtime overhead 0.6 GB
Free 147.6 GB of 190.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 69.9 GB | 73.0 GB | 128K | 46 | −0.1% ppl | Long context |
| Q6_K | 53.9 GB | 57.0 GB | 128K | 60 | −0.4% ppl | Long context |
| Q5_K_M | 46.6 GB | 49.7 GB | 128K | 69 | −0.8% ppl | Long context |
| Q4_K_M | 39.7 GB | 42.8 GB | 128K | 81 | −1.9% ppl | Recommended |
| Q3_K_M | 32.1 GB | 35.2 GB | 128K | 100 | −5.4% ppl | Long context |
| Q2_K | 27.5 GB | 30.6 GB | 128K | 117 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.
How to run it
$ ollama pull llama3.3:70b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run llama3.3:70b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 39.7 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03There is room to go to the model's full 128K context on this card.