What GPU do I need to run lightseekorg/kimi-k2.6-eagle3-mla?
3.0B parameters, published in BF16. View on Hugging Face
Set up kimi-k2.6-eagle3-mlakimi-k2.6-eagle3-mla is published by lightseekorg on Hugging Face, with 112,398 downloads and 7 likes to date. It's a Eagle3DeepseekV2ForCausalLM model built for text-generation, published natively in BF16.
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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 5.6 GB | 6.7 GB | RTX 5060 Ti | 1 | $0.110/hr |
| FP8 (quantized) | 2.8 GB | 3.4 GB | RTX 5060 Ti | 1 | $0.110/hr |
| INT4 (quantized) | 1.4 GB | 1.7 GB | RTX 5060 Ti | 1 | $0.110/hr |
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 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run kimi-k2.6-eagle3-mla at its published (BF16) precision: 1× RTX 5060 Ti, at $0.110/hr per GPU ($0.110/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
kimi-k2.6-eagle3-mla: common questions
Does kimi-k2.6-eagle3-mla fit on a 8 GB GPU?
Yes. At BF16 it needs 6.7 GB of VRAM, so an 8 GB card holds it with 1.3 GB to spare. A 6 GB card is not enough for it at BF16.
How many copies of kimi-k2.6-eagle3-mla fit on one RTX 5060 Ti?
2, by VRAM alone. That card carries 16.0 GB and one copy needs 6.7 GB at BF16, on a live rate of $0.110/hr for the whole card. Throughput is not modelled here, so 2 copies is not 2 times the requests served.
What is the least VRAM kimi-k2.6-eagle3-mla can run in?
1.7 GB, at INT4 (quantized), which fits a 6 GB card, against 6.7 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Kimi K2 models
- Kimi-K2-Instruct (1026.4B, F8_E4M3)
- Kimi-K2-Base (1026.5B, F8_E4M3)
- Kimi-K2-Instruct-0905 (1026.5B, F8_E4M3)
- Kimi-K2.5 (1026.9B, Native INT4)
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
