Won't fitfp16 · 4K ctx · batch 1

Does RTX 5090 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. RTX 5090 only has 32 GB, short by 79.2 GB. INT4 quantization brings it down to 28.9 GB — that fits. For fp16 accuracy, move to H200.

347%
VRAM
Won't fit
Estimated VRAM (fp16)
111.2 GB
of 32 GB on RTX 5090· 79.2 GB short
Tok/sec
79
TFTT
1538ms
Power
325W
Rent on GPUniq marketplace
RTX 5090
Live prices from verified providers · billed hourly, no commitment.
Rent now

Memory breakdown (fp16)

Shared Weights
14.00 GB
Expert Weights
93.40 GB
KV Cache
0.50 GB
Activations
2.00 GB
Framework Overhead
1.27 GB

Quantization comparison

Lower precision = less VRAM with a small quality trade-off. Quality order: FP16 > INT8 > INT4.

PrecisionVRAMUtilisationFits on RTX 5090?
FP16 (full precision)111.2 GB347%Won't fit
INT8 (8-bit)56.3 GB176%Won't fit
INT4 / Q4 (4-bit)28.9 GB90%⚠️Tight fit

Frequently asked

Can RTX 5090 run Mixtral-8x7B-v0.1?
Not at fp16 — Mixtral-8x7B-v0.1 needs about 111.2 GB while RTX 5090 has 32 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 RTX 5090?
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 RTX 5090, enable Flash Attention 2.
Where can I rent a RTX 5090?
GPUniq aggregates live RTX 5090 offers from verified providers. You can deploy an instance in about a minute and pay hourly with no commitment.
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.

Open in chat
Want to tweak sequence length, batch size, or fine-tuning? Open the full calculator →