StableLM 2 12B needs ~29.7 GB VRAM. NVIDIA A100 80GB has 80.0 GB. With Q5_K_M quantization, expect ~152 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
151.6 tok/s
TTFT
1277 ms
Safe context
4K
Memory
29.7 GB / 80.0 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 | C | Runs well | 151.6 tok/s | 696 ms | 4K |
| Coding | C | Runs well | 151.6 tok/s | 1277 ms | 4K |
| Agentic Coding | C | Runs well | 151.6 tok/s | 1857 ms | 4K |
| Reasoning | C | Runs well | 151.6 tok/s | 1509 ms | 4K |
| RAG | C | Runs well | 151.6 tok/s | 2321 ms | 4K |
How StableLM 2 12B (12B params) fits at each quantization level on NVIDIA A100 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 4.7 GB | Low | D39 |
Q3_K_S | 3 | 5.9 GB | Low | D40 |
NVFP4 | 4 |
Copy-paste commands to run StableLM 2 12B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "stabilityai/stablelm-2-12b-chat" \
--hf-file "stablelm-2-12b-chat-Q5_K_M.gguf" \
-c 4096 -ngl 99Yes, NVIDIA A100 80GB can run StableLM 2 12B with a C grade (Runs well). Expected decode speed: 151.6 tok/s.
StableLM 2 12B (12B parameters) requires approximately 29.7 GB of memory with Q5_K_M quantization.
The recommended quantization for StableLM 2 12B is Q5_K_M, which balances quality and memory efficiency.
On NVIDIA A100 80GB, StableLM 2 12B achieves approximately 151.6 tokens per second decode speed with a time-to-first-token of 1277ms using Q5_K_M quantization.
For coding workloads, StableLM 2 12B on NVIDIA A100 80GB receives a C grade with 151.6 tok/s and 4K context.
On NVIDIA A100 80GB, StableLM 2 12B can safely use up to 4K tokens of context. The model's official context limit is 4K, 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/stablelm-2-12b-on-a100-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
6.7 GB |
| Medium |
| D40 |
Q4_K_M | 4 | 7.3 GB | Medium | D40 |
Q5_K_M | 5 | 8.6 GB | High | D40 |
Q6_K | 6 | 9.8 GB | High | D40 |
Q8_0 | 8 | 12.8 GB | Very High | C40 |
F16Best for your GPU | 16 | 24.6 GB | Maximum | C42 |