RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?API pricesVRAM calculatorNew

Can Qwen2.5 VL 7B Instruct run on the H100 SXM?

Yes. At 8K context the best fit is F16, using about 15.3 GB of the 76.0 GB usable on the H100 SXM. Estimated speed ceiling: ~220 tokens/sec.

+ 1.3 GB with image input. The figures on this page are for text only. Sending images also loads the vision projector (mmproj) file: F16 at 8K context then needs about 16.6 GB (still fits). Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •3.7 GB Fits3.9 GB Fits5.2 GB Fits1111
3-bit (Q3_K_M) •4.5 GB Fits4.7 GB Fits6.0 GB Fits880
4-bit (Q4_K_M) •5.3 GB Fits5.5 GB Fits6.8 GB Fits715
5-bit (Q5_K_M) •6.0 GB Fits6.2 GB Fits7.5 GB Fits615
6-bit (Q6_K) •6.7 GB Fits7.0 GB Fits8.3 GB Fits536
8-bit (Q8_0) •8.5 GB Fits8.7 GB Fits10.0 GB Fits414
16-bit (F16/BF16) •15.1 GB Fits15.3 GB Fits16.6 GB Fits220

• real GGUF file size from bartowski/Qwen_Qwen2.5-VL-7B-Instruct-GGUF. Speed is a bandwidth ceiling (3350 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

Qwen2.5 VL 7B Instruct on every GPU and Mac · Every model that runs on the H100 SXM · Other models that fit 64 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (Qwen/Qwen2.5-VL-7B-Instruct), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.