Devstral 2 123B Instruct needs ~100.5 GB VRAM. AMD Instinct MI300X 192GB has 192.0 GB. With Q4_K_M quantization, expect ~60 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
59.9 tok/s
TTFT
3231 ms
Safe context
256K
Memory
100.5 GB / 192.0 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 | S | Runs well | 59.9 tok/s | 1762 ms | 256K |
| Coding | S | Runs well | 59.9 tok/s | 3231 ms | 256K |
| Agentic Coding | S | Runs well | 59.9 tok/s | 4700 ms | 256K |
| Reasoning | S | Runs well | 59.9 tok/s | 3818 ms | 256K |
| RAG | S | Runs well | 59.9 tok/s | 5875 ms | 256K |
How Devstral 2 123B Instruct (123B params) fits at each quantization level on AMD Instinct MI300X 192GB (192.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 48.0 GB | Low | A84 |
Q3_K_S | 3 | 60.3 GB | Low | S86 |
NVFP4 | 4 |
Copy-paste commands to run Devstral 2 123B Instruct on your machine.
Run
lms load Devstral-2-123B-Instruct-2512 && lms server startYes, AMD Instinct MI300X 192GB can run Devstral 2 123B Instruct with a S grade (Runs well). Expected decode speed: 59.9 tok/s.
Devstral 2 123B Instruct (123B parameters) requires approximately 100.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Devstral 2 123B Instruct is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI300X 192GB, Devstral 2 123B Instruct achieves approximately 59.9 tokens per second decode speed with a time-to-first-token of 3231ms using Q4_K_M quantization.
For coding workloads, Devstral 2 123B Instruct on AMD Instinct MI300X 192GB receives a S grade with 59.9 tok/s and 256K context.
On AMD Instinct MI300X 192GB, Devstral 2 123B Instruct can safely use up to 256K tokens of context. The model's official context limit is 256K, 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/devstral-2-123b-on-instinct-mi300x-192gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
68.9 GB |
| Medium |
| S87 |
Q4_K_M | 4 | 75.0 GB | Medium | S87 |
Q5_K_M | 5 | 88.6 GB | High | S89 |
Q6_K | 6 | 100.9 GB | High | S90 |
Q8_0Best for your GPU | 8 | 131.6 GB | Very High | S91 |
F16 | 16 | 252.2 GB | Maximum | F0 |