❌Won't fitfp16 · 4K ctx · batch 1
Does L40S run Mixtral-8x7B-v0.1? No at fp16.
At fp16 precision, Mixtral-8x7B-v0.1 (47 B MoE parameters) needs roughly 111.2 GB of VRAM. L40S only has 48 GB, short by 63.2 GB. INT4 quantization brings it down to 28.9 GB — that fits. For fp16 accuracy, move to H200.
232%
VRAM
Won't fit
Estimated VRAM (fp16)
111.2 GB
of 48 GB on L40S· 63.2 GB short
Tok/sec
85
TFTT
1442ms
Power
198W
Rent on GPUniq marketplace
L40S
Live prices from verified providers · billed hourly, no commitment.
Memory breakdown (fp16)
Shared Weights
14.00 GBExpert Weights
93.40 GBKV Cache
0.50 GBActivations
2.00 GBFramework Overhead
1.27 GBQuantization comparison
Lower precision = less VRAM with a small quality trade-off. Quality order: FP16 > INT8 > INT4.
| Precision | VRAM | Utilisation | Fits on L40S? |
|---|---|---|---|
| FP16 (full precision) | 111.2 GB | 232% | ❌Won't fit |
| INT8 (8-bit) | 56.3 GB | 117% | ❌Won't fit |
| INT4 / Q4 (4-bit) | 28.9 GB | 60% | ✅Runs well |
Frequently asked
- Can L40S run Mixtral-8x7B-v0.1?
- Not at fp16 — Mixtral-8x7B-v0.1 needs about 111.2 GB while L40S has 48 GB. It fits at INT4 quantization (28.9 GB) with some accuracy trade-off. For full precision, use H200 instead.
- How much VRAM does Mixtral-8x7B-v0.1 use?
- About 111.2 GB at fp16, 28.9 GB at INT4 (for a 4K context, batch size 1). Longer contexts add to KV cache size; larger batches increase activations.
- What's the fastest way to run Mixtral-8x7B-v0.1 on L40S?
- Use a production inference engine like vLLM, SGLang, or TensorRT-LLM with paged attention — they cut KV cache 2–3× vs the naive estimate and batch multiple requests efficiently. For L40S, enable Flash Attention 2.
- Where can I rent a L40S?
- GPUniq aggregates live L40S offers from verified providers. You can deploy an instance in about a minute and pay hourly with no commitment.
Other GPUs for Mixtral-8x7B-v0.1
Try it live
Chat with Mixtral-8x7B-v0.1 — no setup
Send a prompt and see how Mixtral-8x7B-v0.1 responds directly in our chat. No installation, no GPU required to test.
Want to tweak sequence length, batch size, or fine-tuning? Open the full calculator →