Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
86.9 tok/s
TTFT
2228 ms
Safe context
30K
Memory
67.6 GB / 128.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 86.9 tok/s | 3241 ms | 52K |
| Chat | C | Runs well | 86.9 tok/s | 1215 ms | 16K |
| Coding | C | Runs well | 86.9 tok/s | 2228 ms | 30K |
| RAG | B | Runs well | 86.9 tok/s | 4051 ms | 52K |
| Reasoning | C | Runs well | 86.9 tok/s | 2633 ms | 30K |
How Llama 3.3 70B (70B params) fits at each quantization level on AMD Instinct MI300A 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 27.3 GB | Low | D34 |
Q3_K_S | 3 | 34.3 GB | Low | D35 |
NVFP4 | 4 | 39.2 GB | Medium | D36 |
Q4_K_M | 4 | 42.7 GB | Medium | D37 |
Q5_K_M | 5 | 50.4 GB | High | D38 |
Q6_K | 6 | 57.4 GB | High | D39 |
Q8_0Best for your GPU | 8 | 74.9 GB | Very High | C42 |
F16 | 16 | 143.5 GB | Maximum | F0 |
ollama run llama-3.3-70bhuggingface-cli download llama-3.3-70b