NVIDIA H200 141GBOpção econômica141 GB VRAM (+13)4800 GB/s (+1600)
A
Raises estimated decode speed by about 62%.97.4 tok/s decodificação
Raises estimated decode speed by about 62%.
~$30,000 MSRP
Can Mixtral 8x22B run on AMD Instinct MI250X 128GB?
YES — Runs Great
B69Good
Estimated from fit model
Mixtral 8x22B needs ~103.1 GB VRAM. AMD Instinct MI250X 128GB has 128.0 GB. With Q4_K_M quantization, expect ~60 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced
Operating mode
Choose the run profile you care about
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
Q4_K_M (Medium quality) — 103.1 GB, 60.3 tok/s, Runs well
103.1 GB required128.0 GB available
81% VRAM used
Fit status
Runs well
Decode
60.3 tok/s
TTFT
3210 ms
Safe context
66K
Memory
103.1 GB / 128.0 GB
Memory breakdown
Weights86.0 GB
KV Cache3.4 GB
Runtime0.9 GB
Headroom12.8 GB
See how fast it feels
See how fast it feelsMixtral 8x22B on AMD Instinct MI250X 128GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.
Given information:
- Speed = 60 mph (miles per hour)
- Time = 2.5 hours
Formula: Distance = Speed x Time
Calculation:
Distance = 60 mph x 2.5 h
= 150 miles
The train travels 150 miles.
Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.
Breakdown:
- First half: 1.25 hours at 60 mph = 75 miles
- Stop: 20 minutes (no distance)
- Second half: 1.25 hours at 60 mph = 75 miles
Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph
The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 60.3 tok/s decode · 3.2s TTFT (warm) · 151 tok/s prefill
What limits this setup
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.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 60.3 tok/s | 1751 ms | 66K |
| Coding | B | Runs well | 60.3 tok/s | 3210 ms | 66K |
| Agentic Coding | B | Tight fit | 60.3 tok/s | 4669 ms | 66K |
| Reasoning | B | Runs well | 60.3 tok/s | 3794 ms | 66K |
| RAG | B | Tight fit | 60.3 tok/s | 5837 ms | 66K |
Inference speed
Mixtral 8x22B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Mixtral 8x22B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~14 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? |
|---|---|---|---|---|
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 13.5 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 9.2 | Heavy offload |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 8.7 | Heavy offload |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 6.8 | Heavy offload |
2× RX 7900 XTX 24GB | 48 GB | Q4_K_M | 5.0 | Too big |
| RTX 5090 32GB | 32 GB | Q4_K_M | 3.9 | Too big |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 3.7 | Too big |
| 2× RTX 4090 24GB | 48 GB | Q4_K_M | 3.4 | Too big |
| 2× RTX 3090 24GB | 48 GB | Q4_K_M | 2.9 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 2.6 | Too big |
| 4× RTX 3060 12GB | 48 GB | Q4_K_M | 2.6 | Too big |
| RTX 4090 24GB | 24 GB | Q4_K_M | 2.5 | Too big |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 2.5 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 2.4 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 2.3 | Too big |
| RTX 3090 24GB | 24 GB | Q4_K_M | 2.1 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 2.0 | 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.
Quantization options
How Mixtral 8x22B (141B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 55.0 GB | Low | B59 |
Q3_K_S | 3 | 69.1 GB | Low | B61 |
NVFP4 | 4 | 79.0 GB | Medium | B61 |
Q4_K_M | 4 | 86.0 GB | Medium | B61 |
Q5_K_MBest for your GPU | 5 | 101.5 GB | High | B61 |
Q6_K | 6 | 115.6 GB | High | F0 |
Q8_0 | 8 | 150.9 GB | Very High | F0 |
F16 | 16 | 289.0 GB | Maximum | F0 |
Get started
Copy-paste commands to run Mixtral 8x22B on your machine.
Run
ollama run mixtral:8x22bOpções de upgrade
Hardware que roda bem Mixtral 8x22B
Frequently asked questions
Can AMD Instinct MI250X 128GB run Mixtral 8x22B?
Yes, AMD Instinct MI250X 128GB can run Mixtral 8x22B with a B grade (Runs well). Expected decode speed: 60.3 tok/s.
How much VRAM does Mixtral 8x22B need?
Mixtral 8x22B (141B parameters) requires approximately 103.1 GB of memory with Q4_K_M quantization.
What is the best quantization for Mixtral 8x22B?
The recommended quantization for Mixtral 8x22B is Q4_K_M, which balances quality and memory efficiency.
What speed will Mixtral 8x22B run at on AMD Instinct MI250X 128GB?
On AMD Instinct MI250X 128GB, Mixtral 8x22B achieves approximately 60.3 tokens per second decode speed with a time-to-first-token of 3210ms using Q4_K_M quantization.
Can AMD Instinct MI250X 128GB run Mixtral 8x22B for coding?
For coding workloads, Mixtral 8x22B on AMD Instinct MI250X 128GB receives a B grade with 60.3 tok/s and 66K context.
What context window can Mixtral 8x22B use on AMD Instinct MI250X 128GB?
On AMD Instinct MI250X 128GB, Mixtral 8x22B can safely use up to 66K tokens of context. The model's official context limit is 66K, but available memory constrains the safe maximum.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/mixtral-8x22b-on-instinct-mi250x-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: