What GPU do I need to run moonshotai/Kimi-K2-Instruct-0905?
A 1026B (MoE) language model for chat and instruction-following. 1026.5B parameters, published in F8_E4M3. View on Hugging Face
Kimi-K2-Instruct-0905 is published by moonshotai on Hugging Face, with 38,392 downloads and 786 likes to date. It's a DeepseekV3ForCausalLM model built for text-generation, published natively in F8_E4M3.
What Kimi-K2-Instruct-0905 is
Kimi-K2-Instruct-0905 is a 1026B-parameter mixture-of-experts language model published by Moonshot AI on Hugging Face. It is released under Custom license.
License note: a lab-specific license (tagged "other" on Hugging Face); read the model card's own license section before commercial use. Facts in this section are sourced from Kimi-K2-Instruct-0905's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Chat assistants
- Instruction following
- Synthetic data generation
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) |
|---|---|---|---|---|---|
| FP8 (native) | 956.0 GB | 1147.2 GB | No capable live offer found | – | – |
| INT4 (quantized) | 478.0 GB | 573.6 GB | RTX PRO 6000 WS | 6 | $8.99/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.
Kimi-K2-Instruct-0905: common questions
Can Kimi-K2-Instruct-0905 run on a single GPU?
Not on a desktop card. At FP8 (native) it needs 1147.2 GB of VRAM, more than a single 32 GB desktop card holds. No card currently listed on the marketplace both supports FP8 (native) and has enough VRAM for it, so how many it would take is not something this page can answer today.
Is Kimi-K2-Instruct-0905 already quantized?
Yes. It is published in FP8, one byte per parameter, so the 1147.2 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 573.6 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.
How to run Kimi-K2-Instruct-0905
Run Kimi-K2-Instruct-0905 with vLLM
From moonshotai/Kimi-K2-Instruct-0905's own deployment docs.
# start ray on node 0 and node 1
# node 0:
vllm serve $MODEL_PATH \
--port 8000 \
--served-model-name kimi-k2 \
--trust-remote-code \
--tensor-parallel-size 16 \
--enable-auto-tool-choice \
--tool-call-parser kimi_k2Source: https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905/raw/main/docs/deploy_guidance.md
Run Kimi-K2-Instruct-0905 with GGUF quantizations
Prebuilt GGUF weights published at unsloth/Kimi-K2-Instruct-0905-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/Kimi-K2-Instruct-0905-GGUFSource: https://huggingface.co/unsloth/Kimi-K2-Instruct-0905-GGUF
Deploy Kimi-K2-Instruct-0905 on Aquanode
Aquanode has no one-click deploy template for Kimi-K2-Instruct-0905; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1147 GB VRAM or more).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU podWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Kimi K2 models
- Kimi-K2-Base (1026.5B, F8_E4M3)
- Kimi-K2-Instruct (1026.4B, F8_E4M3)
- Kimi-K2.5 (1026.9B, Native INT4)
- kimi-k2.6-eagle3-mla (3.0B, BF16)
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
