Moonshot AI, China · Released November 4, 2026New
Kimi K3.1 Pro has 2780.1B parameters (106B active per token). In BF16 its weights alone take 5178 GiB; quantized to 4-bit, about 1563 GiB. Each 32K-token request adds 0.84 GiB of KV cache. Cheapest way to run it today: 6 × AMD MI355X / MI350X (288 GB) at $51.60 per hour. It reads text, images and video, calls tools and has a reasoning mode.
Size your own setup in the calculator →Weights plus the KV cache of one request (BF16 cache) and the model's fixed recurrent state, in GiB. Add 1 to 3 GiB for the inference engine itself.
| Weights format | Weights only | + 8K context | + 32K context | + 128K context | + 1M context |
|---|---|---|---|---|---|
| NVFP4 (native) | 1454 | 1455 | 1455 | 1458 | 1481 |
| BF16 / FP16 | 5178 | 5179 | 5180 | 5182 | 5206 |
| FP8 / INT8 | 2591 | 2592 | 2593 | 2595 | 2619 |
| 4-bit (GGUF Q4_K_M) | 1563 | 1564 | 1565 | 1567 | 1591 |
Fewest GPUs that fit the weights plus one 8K-token request. Data-center GPUs use vLLM (90% of memory usable), the others llama.cpp. Several GPUs split the model with tensor or pipeline parallelism.
| GPU | NVFP4 (native) | BF16 / FP16 | 8-bit | 4-bit |
|---|---|---|---|---|
| GeForce RTX 4090 24 GB | Not on this GPU | > 128 | > 128 | 96 (several machines) |
| GeForce RTX 5090 32 GB | Not on this GPU | > 128 | 96 (several machines) | 64 (several machines) |
| RTX PRO 6000 Blackwell 96 GB | Not on this GPU | 64 (several machines) | 32 (several machines) | 24 (several machines) |
| Mac M5 Max 128 GB 96 GB usable | Not on this GPU | 64 (several machines) | 32 (several machines) | 24 (several machines) |
| Ryzen AI Max+ 395 128 GB 96 GB usable | Not on this GPU | 64 (several machines) | 32 (several machines) | 24 (several machines) |
| DGX Spark (GB10) 128 GB | Not on this GPU | 48 (several machines) | 24 (several machines) | 16 (several machines) |
| NVIDIA H100 80 GB | Not on this GPU | 96 (several servers) | 48 (several servers) | 24 (several servers) |
| NVIDIA H200 141 GB | Not on this GPU | 48 (several servers) | 24 (several servers) | 16 (several servers) |
| NVIDIA B200 (HGX) 180 GB | 16 (several servers) | 48 (several servers) | 24 (several servers) | 16 (several servers) |
8-bit: FP8 with vLLM (INT8 on GPUs without FP8), Q8_0 with llama.cpp. 4-bit: AWQ / GPTQ with vLLM, Q4_K_M with llama.cpp, both counted at the Q4_K_M size. Not on this GPU: the official NVFP4 weights do not run there (llama.cpp needs a GGUF version, and vLLM needs a GPU with FP4 support).
For each GPU: the fewest cards that fit Kimi K3.1 Pro with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-11-05).
| Setup | Per hour | Weights | Provider | Per month | Rent |
|---|---|---|---|---|---|
| 6 × AMD MI355X / MI350X 288 GB | $51.60 | NVFP4 (official) | Oracle Cloud | $37,668.00 | Rent 6 × AMD MI355X / MI350X on Oracle Cloud (opens in a new tab) → |
| 7 × NVIDIA B300 / GB300 288 GB | $59.15 | NVFP4 (official) | Scaleway | $43,179.50 | Rent 7 × NVIDIA B300 / GB300 on Scaleway (opens in a new tab) → |
On-demand prices from AWS, Google Cloud, Azure, RunPod, Vast.ai, Oracle Cloud, OVHcloud, Scaleway, Verda, Akash and UpCloud, checked every hour. Serving many users needs more KV cache, so more memory: size it in the calculator. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.
AWS, Google Cloud and UpCloud prices: Spare Cores (opens in a new tab), CC BY-SA 4.0 (opens in a new tab), shared under the same license.
The repository sets no sampling defaults: these are OpenRouter's defaults for Kimi K3.1 Pro.
| Setting | Value |
|---|---|
| Top-p | 0.95 |
With llama.cpp, pass them yourself: --top-p 0.95
Reasoning. Has a reasoning mode. Reasoning tokens take context and KV cache like any other token: leave room for them.
Architecture: 93 layers · MLA (512 + 64 latent) on 24 · 69 Kimi Delta Attention. Its KV cache is 3.9× smaller than if every layer used full attention, because only 24 of its 93 layers keep a KV cache; the others hold a small fixed-size state. Only 106B parameters are active per token, but all 2780B must sit in memory: VRAM depends on the total, speed on the active part.
| Context per request | BF16 cache | FP8 cache |
|---|---|---|
| 8K tokens | 0.21 GiB | 0.11 GiB |
| 32K tokens | 0.84 GiB | 0.42 GiB |
| 128K tokens | 3.38 GiB | 1.69 GiB |
| 1M tokens | 27.0 GiB | 13.5 GiB |
Plus 429 MiB of recurrent state per request, whatever the context.
In BF16 the weights alone take 5178 GiB (5560 GB). In FP8 that is 2591 GiB, and about 1563 GiB with 4-bit quantization (Q4_K_M); the official NVFP4 checkpoint is 1454 GiB. Each request then adds KV cache: 0.21 GiB at 8K tokens and 0.84 GiB at 32K (BF16 cache).
No. Even in 4-bit it needs 96 RTX 4090s, spread over several machines. In 4-bit it needs 24 H100 GPUs, across several servers.
No. Even in 4-bit it needs 64 RTX 5090s, spread over several machines.
No single Mac holds it, even in 4-bit: it needs 1564 GiB with an 8K-token context, and the largest Mac (512 GB) gives its GPU about 384 GB.
No. Even in 4-bit it needs 16 DGX Spark units or 24 Ryzen AI Max+ 395 machines (128 GB), linked over the network.
On 2026-11-05, the cheapest on-demand setup is 6 × AMD MI355X / MI350X (288 GB) with NVFP4 weights on Oracle Cloud, at $51.60 per hour (about $37,668.00 per month). Next: 7 × NVIDIA B300 / GB300 (288 GB) with NVFP4 weights on Scaleway, at $59.15 per hour. Sized for one 8K-token request; prices are checked every hour.
With one request and an 8K-token context: 96 in BF16, 48 in FP8 and 24 in 4-bit (vLLM, 90% of memory usable). Above 8 GPUs, that means several servers. Serving many users at once needs more memory for their KV caches: the calculator sizes that for you.
Yes. Kimi K3.1 Pro reads text, images and video. Images add tokens to the context, so they also add KV cache.
Yes, Kimi K3.1 Pro supports tool (function) calling: it can ask your application to run a function and use the result.
Has a reasoning mode. Reasoning tokens count toward the context and the KV cache.
The repository sets no defaults; OpenRouter uses top-p 0.95.
For a model card or a README: the 4-bit size and the smallest GPU it fits on, linked to this page. Data as JSON: /api/models/kimi-k3-1-pro.json.
Moonshot AI, China · Released November 4, 2026[](https://studiotvai.com/vram-requirements/kimi-k3-1-pro)Same family (large moe): MiniMax M3.1 Flash · MiniMax M3 · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · Atria Dawn · Atria Dawn Preview · Hy4 Preview · K-EXAONE 2.0 750B-A37B · Inkling · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Muse Spark Open · Beam 1.0 501B-A23B · Kimi K3 · Mistral Large 4 · Mistral Large 3 · Mistral Small 4 119B · Leanstral 1.5 119B-A6B · Mixtral 8x22B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Intern S2 397B · DeepSeek V3 · DeepSeek V3.1 · Kimi K2.7 Code · Kimi K2.5 · Kimi K2 · GLM-5.2 · GLM-5.1 · GLM-5 · MiniMax M2.5 · MiniMax M2 · MiMo-V2.5 · Ornith-1.0 397B · Qwen3 235B-A22B · Qwen3.5 397B-A17B · GLM-4.7 · GLM-4.5 · Ling-3.1-flash · Step 5 Preview · Hy3
Llama 3.1 8B · Llama 3 8B · Llama 3.2 3B · Nanbeige4.3 33B · Granite 4.2 30B · Granite 4.2 8B · Granite 4.2 3B · MiniCPM5 2B · MiniCPM5 1B · Ministral 3 14B · Ministral 3 8B · Ministral 3 3B · Devstral 2 123B · Devstral Small 2 24B · Mistral Medium 3.5 128B · Magistral Small 1.2 24B · Mistral Small 3 24B · Mistral Large 2411 123B · Pixtral Large 124B · Codestral 22B · Mistral Small 2409 22B · Pixtral 12B · Nemotron 3.5 Parse · Gemma 2 9B · Gemma 3 4B · LLaVA 1.6 Mistral 7B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 405B · Hy-Memory 30B-A3B · Kimi VL A3B Instruct · Mixtral 8x7B · Unlimited-OCR · Unlimited-OCR 2 · Xing4.0 29B-A4B · Qwen3.5 4B · MiniCPM-V-4.7 1B · Raon-1 mini preview · Qwen3.5 9B · Qwen3.8 27B · Qwen3.6 35B-A3B · Clover 35B-A3B Preview · SenseNova Loop 9B Preview · Qwen3.5 122B-A10B · Qwen3.8-Flash-Next · LFM3 1.7B · LFM3-VL 2B · d1 2B · LFM2.5 8B-A1B · LFM2 24B-A2B · Gemma 4 12B · Gemma 4 31B · Gemma 4 26B-A4B · gpt-oss 20B · gpt-oss 120B · Llama 4 Scout 17B-16E · Llama 4 Maverick 17B-128E · Kolibri-1 · Recursive Flint · Nemotron Labs Dory 1.0 4B · Step 3.5 Flash · Step 3.7 Flash · Laguna S 2.1 · Laguna XS 2.1 · Command A+ · Inkling Small · Muse Glimmer 30B · Nemotron 3 Nano 30B-A3B · Nemotron 3 Super 120B-A12B · Nemotron 3 Ultra 550B-A55B · Mamba-Codestral 7B · Nemotron 3.5 Super VL 120B-A12B · Nemotron 3.5 Bolt 74B-A9B · MiniMax M3.1 Flash · MiniMax M3 · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · Atria Dawn · Atria Dawn Preview · Hy4 Preview · K-EXAONE 2.0 750B-A37B · Inkling · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Muse Spark Open · Beam 1.0 501B-A23B · Kimi K3 · Mistral Large 4 · Mistral Large 3 · Mistral Small 4 119B · Leanstral 1.5 119B-A6B · Mixtral 8x22B · Qwen3-Coder-Next 80B-A3B · Qwen3-Coder 30B-A3B · Qwen3-Coder 480B-A35B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Ornith 1.5 35B-A3B · Ornith 1.5 9B · Intern S2 397B · Clef · Clef Flash · d1 3B · Humanizer · JEV 27B VL · Mellum2.1 12B-A2.5B · LightOnOCR-3 4B · Spark-X2.5 4B · Agnes-3.0-Qwen · Youtu-Parsing-Omni · Agnes-3.0-Flash · Mistral 7B v0.3 · Mistral Small 3.1 24B · Mistral Nemo · Ministral 8B · DeepSeek V3 · DeepSeek R1 Qwen3 8B · DeepSeek R1 Distill Qwen 32B · DeepSeek V3.1 · DeepSeek R1 Distill Qwen 14B · DeepSeek R1 Distill Qwen 7B · DeepSeek R1 Distill Llama 8B · Qwen3 4B · Qwen3 8B · Qwen2.5 7B · Qwen3 14B · Qwen2.5 3B · Qwen3.6 27B · Qwen3.5 27B · Qwen2.5-Coder 7B · Qwen2.5 32B · Qwen2.5-Coder 14B · Qwen3.5 35B-A3B · Qwen3 30B-A3B · Qwen2.5 14B · Qwen2.5-Coder 32B · Kimi K2.7 Code · Kimi K2.5 · Kimi K2 · GLM-5.2 · GLM-5.1 · GLM-5 · MiniMax M2.5 · MiniMax M2 · MiMo-V2.5 · Ornith-1.0 397B · Qwen2.5-Coder 3B · Qwen3 235B-A22B · Qwen3.5 397B-A17B · Gemma 4 E4B · Gemma 4 E2B · Nemotron 3 Nano 4B · Nemotron 3.5 Lightning 30B-A3B · MiniCPM-V-4.7 35B-A3B · LFM2.5 24B-A2B · GLM-4.7 · Qwen3-VL 8B · Qwen2.5-VL 7B · Qwen3-VL 4B · Qwen2.5-VL 3B · Qwen2.5-VL 32B · Qwen2-VL 7B · GLM-4.5-Air · GLM-4.5 · phi-4 · Phi-3.5-mini · Phi-4-mini · Phi-3-mini-128k · Ling-3.1-flash · Step 5 Preview · Hy3 · Ornith-1.5 122B · Spark-X2.6 4B · Sage-A1.5 · MLExpert · Agents-A1 4B · Ling-3.0-flash-Sante · MiniCPM-OCR-1.0 · WeVisOne-VL 4B · Granite 4.1 3B · Qwen3-VL 30B-A3B · Mage-VL-Cowork · Spark-X2.6 1.7B · Qwen3.5 4B-Qwenputer · 6.8-Code2Video
Estimates, not guarantees: computed from the official config.json with the same engine as the LLM VRAM Calculator. Real usage depends on your engine version and settings.