LLaVA 1.6 13B needs ~23.7 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~26 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 with offload
Decode
25.7 tok/s
TTFT
7521 ms
Safe context
4K
Memory
23.7 GB / 24.0 GB
This setup is broadly balanced for this model.
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.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 25.7 tok/s | 4102 ms | 4K |
| Coding | A | Runs with offload | 25.7 tok/s | 7521 ms | 4K |
| Agentic Coding | F | Too heavy | 7.7 tok/s | 36410 ms | 4K |
| Reasoning | A | Runs with offload | 25.7 tok/s | 8888 ms | 4K |
| RAG | F | Too heavy | 7.7 tok/s | 45512 ms | 4K |
How LLaVA 1.6 13B (13B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.1 GB | Low | B69 |
Q3_K_S | 3 | 6.4 GB | Low | B70 |
NVFP4 | 4 |
Copy-paste commands to run LLaVA 1.6 13B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "liuhaotian/llava-v1.6-mistral-7b" \
--hf-file "llava-v1.6-mistral-7b-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 30.5B | S | 30.9 tok/s | ||
| 27B | S | 13.4 tok/s |
Yes, Tesla P40 24GB can run LLaVA 1.6 13B with a A grade (Runs with offload). Expected decode speed: 25.7 tok/s.
LLaVA 1.6 13B (13B parameters) requires approximately 23.7 GB of memory with Q4_K_M quantization.
The recommended quantization for LLaVA 1.6 13B is Q4_K_M, which balances quality and memory efficiency.
On Tesla P40 24GB, LLaVA 1.6 13B achieves approximately 25.7 tokens per second decode speed with a time-to-first-token of 7521ms using Q4_K_M quantization.
For coding workloads, LLaVA 1.6 13B on Tesla P40 24GB receives a A grade with 25.7 tok/s and 4K context.
On Tesla P40 24GB, LLaVA 1.6 13B 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/llava-1.6-13b-on-tesla-p40-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
7.3 GB |
| Medium |
| A70 |
Q4_K_M | 4 | 7.9 GB | Medium | A71 |
Q5_K_M | 5 | 9.4 GB | High | A71 |
Q6_K | 6 | 10.7 GB | High | A72 |
Q8_0Best for your GPU | 8 | 13.9 GB | Very High | A73 |
F16 | 16 | 26.7 GB | Maximum | F0 |
| 27B | S | 13.4 tok/s |
| 30B | S | 31.9 tok/s |
| 35B | A | 16.7 tok/s |
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.