Mixtral 8x22B needs ~93.5 GB but AMD Instinct MI100 32GB only has 32.0 GB. Try a smaller quantization or lighter model.
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
61.5 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
2.9 tok/s
TTFT
66920 ms
Safe context
4K
Memory
93.5 GB / 32.0 GB
Offload
70%
Usable VRAM is the main blocker for this model.
Not enough usable memory
The model needs 93.5 GB, but this setup only exposes 32.0 GB of usable VRAM.
Add more VRAM headroom
The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 2.9 tok/s | 36502 ms | 4K |
| Coding | F | Too heavy | 2.9 tok/s | 66920 ms | 4K |
| Agentic Coding | F | Too heavy | 2.9 tok/s | 97339 ms | 4K |
| Reasoning | F | Too heavy | 2.9 tok/s | 79088 ms | 4K |
| RAG | F | Too heavy | 2.9 tok/s | 121673 ms | 4K |
How Mixtral 8x22B (141B params) fits at each quantization level on AMD Instinct MI100 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 55.0 GB | Low | F0 |
Q3_K_S | 3 | 69.1 GB | Low | F0 |
NVFP4 | 4 | 79.0 GB | Medium | F0 |
Q4_K_M | 4 | 86.0 GB | Medium | F0 |
Q5_K_M | 5 | 101.5 GB | High | F0 |
Q6_K | 6 | 115.6 GB | High | F0 |
Q8_0 | 8 | 150.9 GB | Very High | F0 |
F16 | 16 | 289.0 GB | Maximum | F0 |
Upgrade-Optionen
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
ca. $8,000 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
ca. $12,000 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
ca. $15,000 MSRP
No, Mixtral 8x22B requires more memory than AMD Instinct MI100 32GB provides.
Mixtral 8x22B (141B parameters) requires approximately 93.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Mixtral 8x22B is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI100 32GB, Mixtral 8x22B achieves approximately 2.9 tokens per second decode speed with a time-to-first-token of 66920ms using Q4_K_M quantization.
For coding workloads, Mixtral 8x22B on AMD Instinct MI100 32GB receives a F grade with 2.9 tok/s and 4K context.
On AMD Instinct MI100 32GB, Mixtral 8x22B can safely use up to 4K tokens of context. The model's official context limit is 66K, but available memory constrains the safe maximum.
Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/mixtral-8x22b-on-instinct-mi100-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
