Qwen 2.5 72B needs ~78.5 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~145 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
144.6 tok/s
TTFT
1339 ms
Safe context
131K
Memory
78.5 GB / 288.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 144.6 tok/s | 730 ms | 131K |
| Coding | A | Runs well | 144.6 tok/s | 1339 ms | 131K |
| Agentic Coding | A | Runs well | 144.6 tok/s | 1947 ms | 131K |
| Reasoning | A | Runs well | 144.6 tok/s | 1582 ms | 131K |
| RAG | A | Runs well | 144.6 tok/s | 2434 ms | 131K |
Inference speed
Estimated decode speed (tokens/sec) for Qwen 2.5 72B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is 2× RX 7900 XTX 24GB at ~17 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
2× RX 7900 XTX 24GB | 48 GB | Q4_K_M | 16.7 | Heavy offload |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 14.9 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 13.8 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 11.5 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 11.0 | Too big |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 10.9 | Fits |
 2× RTX 4090 24GB | 48 GB | Q4_K_M | 8.8 | Heavy offload |
| RTX 5090 32GB | 32 GB | Q4_K_M | 8.1 | Too big |
| 2× RTX 3090 24GB | 48 GB | Q4_K_M | 8.1 | Heavy offload |
| 4× RTX 3060 12GB | 48 GB | Q4_K_M | 7.1 | Heavy offload |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 5.1 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 4.4 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 4.0 | Too big |
| RTX 4090 24GB | 24 GB | Q4_K_M | 2.8 | Too big |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 2.6 | Too big |
| RTX 3090 24GB | 24 GB | Q4_K_M | 2.4 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 2.3 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How Qwen 2.5 72B (72B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 28.1 GB | Low | B68 |
Q3_K_S | 3 | 35.3 GB | Low | B69 |
NVFP4 | 4 | 40.3 GB | Medium | B69 |
Q4_K_M | 4 | 43.9 GB | Medium | B70 |
Q5_K_M | 5 | 51.8 GB | High | A70 |
Q6_K | 6 | 59.0 GB | High | A71 |
Q8_0 | 8 | 77.0 GB | Very High | A72 |
F16Best for your GPU | 16 | 147.6 GB | Maximum | A77 |
Copy-paste commands to run Qwen 2.5 72B on your machine.
Run
ollama run qwen2.5:72bYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen 3.5 397B A17B | 397B | S | 78.9 tok/s | |
 Devstral 2 123B Instruct | 123B | S | 84.6 tok/s | |
| Qwen 3.5 122B A10B | 122B | S | 234.8 tok/s | |
 DeepSeek V4 Flash | 284B | S | 125.8 tok/s | |
| Mistral Small 4 119B | 119B | S | 254.6 tok/s |
Yes, AMD Instinct MI350X 288GB can run Qwen 2.5 72B with a A grade (Runs well). Expected decode speed: 144.6 tok/s.
Qwen 2.5 72B (72B parameters) requires approximately 78.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Qwen 2.5 72B is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI350X 288GB, Qwen 2.5 72B achieves approximately 144.6 tokens per second decode speed with a time-to-first-token of 1339ms using Q4_K_M quantization.
For coding workloads, Qwen 2.5 72B on AMD Instinct MI350X 288GB receives a A grade with 144.6 tok/s and 131K context.
On AMD Instinct MI350X 288GB, Qwen 2.5 72B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/qwen-2.5-72b-on-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: