Devstral 2 123B Instruct needs ~89.3 GB VRAM. NVIDIA A800 80GB has 80.0 GB. With Q4_K_M quantization, expect ~16 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
9.3 GB over capacity — needs offload or smaller quantization
Fit status
Very compromised (needs ~7.8 GB host RAM)
Decode
15.6 tok/s
TTFT
12440 ms
Safe context
4K
Memory
89.3 GB / 80.0 GB
Offload
10%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
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.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 7.8 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Very compromised (needs ~5.7 GB host RAM) | 16.4 tok/s | 6452 ms | 4K |
| Coding | A | Very compromised (needs ~7.8 GB host RAM) | 15.6 tok/s | 12440 ms | 4K |
| Agentic Coding | A | Very compromised (needs ~11.6 GB host RAM) | 14.1 tok/s | 19926 ms | 4K |
| Reasoning | A | Very compromised (needs ~7.8 GB host RAM) | 15.6 tok/s | 14702 ms | 4K |
| RAG | A | Very compromised (needs ~11.6 GB host RAM) | 14.1 tok/s |
How Devstral 2 123B Instruct (123B params) fits at each quantization level on NVIDIA A800 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 48.0 GB | Low | S91 |
Q3_K_SBest for your GPU | 3 | 60.3 GB | Low | S91 |
Copy-paste commands to run Devstral 2 123B Instruct on your machine.
Run
lms load Devstral-2-123B-Instruct-2512 && lms server startYes, NVIDIA A800 80GB can run Devstral 2 123B Instruct with a A grade (Very compromised (needs ~7.8 GB host RAM)). Expected decode speed: 15.6 tok/s.
Devstral 2 123B Instruct (123B parameters) requires approximately 89.3 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 NVIDIA A800 80GB, Devstral 2 123B Instruct achieves approximately 15.6 tokens per second decode speed with a time-to-first-token of 12440ms using Q4_K_M quantization.
For coding workloads, Devstral 2 123B Instruct on NVIDIA A800 80GB receives a A grade with 15.6 tok/s and 4K context.
On NVIDIA A800 80GB, Devstral 2 123B Instruct can safely use up to 4K 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-a800-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| 24907 ms |
| 4K |
| 4 |
68.9 GB |
| Medium |
| F0 |
Q4_K_M | 4 | 75.0 GB | Medium | F0 |
Q5_K_M | 5 | 88.6 GB | High | F0 |
Q6_K | 6 | 100.9 GB | High | F0 |
Q8_0 | 8 | 131.6 GB | Very High | F0 |
F16 | 16 | 252.2 GB | Maximum | F0 |
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.