What GPU do I need to run RamManavalan/Qwen3-VL-Embedding-8B-FP8?
8.8B parameters, published in F8_E4M3. View on Hugging Face
Qwen3-VL-Embedding-8B-FP8 is published by RamManavalan on Hugging Face, with 416,713 downloads and 4 likes to date. It's a Qwen3VLForConditionalGeneration model built for feature-extraction, published natively in F8_E4M3.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 caveat: requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Qwen3-VL-Embedding-8B-FP8 at its published (F8_E4M3) precision: 1× RTX 4070 on simplepod, at $0.080/hr per GPU ($0.080/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More RamManavalan models
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
- Qwen3.6-35B-A3B-FP8 (36.0B, F8_E4M3)
- Qwen3.5-9B (9.7B, BF16)
- Qwen2.5-7B-Instruct (7.6B, BF16)
