Qwen 2.5 Math 72B needs ~75.3 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With Q4_K_M quantization, expect ~109 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
108.5 tok/s
TTFT
1785 ms
Safe context
4K
Memory
75.3 GB / 256.0 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 | B | Runs well | 108.5 tok/s | 974 ms | 4K |
| Coding | B | Runs well | 108.5 tok/s | 1785 ms | 4K |
| Agentic Coding | B | Runs well | 108.5 tok/s | 2597 ms | 4K |
| Reasoning | B | Runs well | 108.5 tok/s | 2110 ms | 4K |
| RAG | B | Runs well | 108.5 tok/s | 3246 ms | 4K |
How Qwen 2.5 Math 72B (72B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 28.1 GB | Low | C51 |
Q3_K_S | 3 | 35.3 GB | Low | C52 |
NVFP4 | 4 | 40.3 GB | Medium | C52 |
Q4_K_M | 4 | 43.9 GB | Medium | C52 |
Q5_K_M | 5 | 51.8 GB | High | C53 |
Q6_K | 6 | 59.0 GB | High | C54 |
Q8_0 | 8 | 77.0 GB | Very High | B55 |
F16Best for your GPU | 16 | 147.6 GB | Maximum | B61 |
Copy-paste commands to run Qwen 2.5 Math 72B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "Qwen/Qwen2.5-Math-72B-Instruct" \
--hf-file "Qwen2.5-Math-72B-Instruct-Q4_K_M.gguf" \
-c 4096 -ngl 99Yes, AMD Instinct MI325X 256GB can run Qwen 2.5 Math 72B with a B grade (Runs well). Expected decode speed: 108.5 tok/s.
Qwen 2.5 Math 72B (72B parameters) requires approximately 75.3 GB of memory with Q4_K_M quantization.
The recommended quantization for Qwen 2.5 Math 72B is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI325X 256GB, Qwen 2.5 Math 72B achieves approximately 108.5 tokens per second decode speed with a time-to-first-token of 1785ms using Q4_K_M quantization.
For coding workloads, Qwen 2.5 Math 72B on AMD Instinct MI325X 256GB receives a B grade with 108.5 tok/s and 4K context.
On AMD Instinct MI325X 256GB, Qwen 2.5 Math 72B can safely use up to 4K tokens of context. The model's official context limit is 4K, 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-math-72b-on-instinct-mi325x-256gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: