Llama 4 Maverick 17B 128E needs ~276.6 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~77 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 with offload
Decode
77.4 tok/s
TTFT
2502 ms
Safe context
78K
Memory
276.6 GB / 288.0 GB
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Runs with offload | 77.4 tok/s | 1364 ms | 78K |
| Coding | S | Runs with offload | 77.4 tok/s | 2502 ms | 78K |
| Agentic Coding | S | Runs with offload | 77.4 tok/s | 3639 ms | 78K |
| Reasoning | S | Runs with offload | 77.4 tok/s | 2956 ms | 78K |
| RAG | S | Runs with offload | 77.4 tok/s | 4548 ms | 78K |
How Llama 4 Maverick 17B 128E (400B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 156.0 GB | Low | A82 |
Q3_K_S | 3 | 196.0 GB | Low | A82 |
NVFP4Best for your GPU | 4 | 224.0 GB | Medium | A82 |
Q4_K_M | 4 | 244.0 GB | Medium | F0 |
Q5_K_M | 5 | 288.0 GB | High | F0 |
Q6_K | 6 | 328.0 GB | High | F0 |
Q8_0 | 8 | 428.0 GB | Very High | F0 |
F16 | 16 | 820.0 GB | Maximum | F0 |
Copy-paste commands to run Llama 4 Maverick 17B 128E on your machine.
Run
lms load Llama-4-Maverick-17B-128E-Instruct && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 480B A35B Instruct | 480B | A | 35.3 tok/s |
Yes, AMD Instinct MI350X 288GB can run Llama 4 Maverick 17B 128E with a S grade (Runs with offload). Expected decode speed: 77.4 tok/s.
Llama 4 Maverick 17B 128E (400B parameters) requires approximately 276.6 GB of memory with Q4_K_M quantization.
The recommended quantization for Llama 4 Maverick 17B 128E is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI350X 288GB, Llama 4 Maverick 17B 128E achieves approximately 77.4 tokens per second decode speed with a time-to-first-token of 2502ms using Q4_K_M quantization.
For coding workloads, Llama 4 Maverick 17B 128E on AMD Instinct MI350X 288GB receives a S grade with 77.4 tok/s and 78K context.
On AMD Instinct MI350X 288GB, Llama 4 Maverick 17B 128E can safely use up to 78K tokens of context. The model's official context limit is 1.0M, but available memory constrains the safe maximum.
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/llama-4-maverick-17b-128e-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: