Kimi K3 — Hardware Requirements & GPU Compatibility
VisionChat
Kimi K3 from Moonshot AI is an enormous model, weighing in at roughly 2.8 trillion parameters, among the largest open-weight releases in this catalogue. It accepts image input alongside text, supporting multimodal chat and visual reasoning in addition to standard dialogue. At this scale, local deployment is not realistic for most users; it needs multi-GPU or server-class hardware, and most people will access it through a hosted endpoint rather than running it on their own machines. Kimi K3 supports a 1M token context window, allowing it to process very long documents, codebases, or conversation histories in one pass. It was released on June 13, 2026, under its own custom license terms rather than a standard Apache or MIT license, so users should review the license text before commercial use.
Kimi K3 runs on a GPU cluster
Q4_K_M needs ~1.7 TB · about 3 nodes of 8× H100 SXM 80 GB
Score 132.8#5 of 107 open#5 of 107 that fit ≤2 TBOther
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
132.8
- 90% range 131.1–134.5
- #5 of 107 open models
- #5 of 107 that fit ≤2 TB
Run Kimi K3
Best fit for your NVIDIA DGX B300. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended for your NVIDIA DGX B300
ollama run hf.co/unsloth/Kimi-K3-GGUFQ4_K_M fits fully · 634.0 GB free · 16K context
Download: Kimi-K3-Q4_K_M.gguf1667.96 GBunsloth
Ways to runOther ways
each opens step-by-stepRun in cloud
Rent 3× 8-GPU H100 SXM nodes · Q4_K_M
- Estimated hourly price
- ~$64.56/hr
- est., whole cluster
- GPUs
- 24 GPUs
- 1.9 TB of VRAM
$5+ bonus for new users
How Much VRAM Does Kimi K3 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On your device | |
|---|---|---|---|---|
| 770.2 GB | 768.3 GB | 2-bit · i-quant extreme compression — Importance-weighted 2-bit, extreme compression — significant quality loss | Fits: 1M context · ~153 tok/s | |
| 1187.2 GB | 1185.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 1M context · ~161 tok/s | |
| 1361.0 GB | 1359 GB | 3-bit medium — 3-bit medium quantization | Fits: 1M context · ~157 tok/s | |
| 1673.7 GB | 1671.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 1M context · ~151 tok/s | |
| 1986.5 GB | 1984.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 1M context · ~144 tok/s | |
| 2299.2 GB | 2297.3 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 64K context · ~139 tok/s | |
| 2785.7 GB | 2783.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 2782 GB | |
| 5565.6 GB | 5563.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 5561.9 GB |
Selected Q4_K_M
4-bit medium quantization1670.0GBat 16K context
- Weights
- 1668.0 GB
- KV cache
- 1.8 GB
- Overhead
- 0.3 GB
Fits NVIDIA DGX B300 · 634.0 GB free · ~151 tok/s
Which Hardware Can Run Kimi K3?
Q4_K_M · 1673.7 GBKimi K3 (Q4_K_M) requires 1673.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2176+ GB is recommended. Using the full 1049K context window can add up to 106.9 GB, bringing total usage to 1780.6 GB. No consumer GPU has enough memory.
Needs server-class hardware
Kimi K3 runs on a GPU cluster · Q4_K_M needs ~1.7 TB
| Hardware | Quant | Memory | Context | Hardware page | |
|---|---|---|---|---|---|
| 8× H200 SXM 141 GB · 1.1 TB | IQ2_XXS | 766.5 GB | 1M ctx | H200 SXM → | IQ2_XXS · 766.5 GB · 1M ctx |
| 8× B200 192 GB · 1.5 TB | Q3_K_M | 1357.3 GB | 128K ctx | B200 → | Q3_K_M · 1357.3 GB · 128K ctx |
| GPU cluster · 3 nodes of 8× H100 SXM 80 GB | Q4_K_M | 1670 GB | 512K ctx | H100 SXM → | Q4_K_M · 1670 GB · 512K ctx |
Also: AMD Instinct MI355X Platform (8x MI355X) · NVIDIA DGX B300 · NVIDIA GB200 NVL72 · NVIDIA GB300 NVL72
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 512 GB: too small for this model (needs ≥ 766.5 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
How good is Kimi K3?
The llmrun Score merges 31 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the ≤2 TB tier
- Kimi K3
- Other models
- Best Score for its VRAM
#5 of 107 that fit ≤2 TBEvery model here fits your NVIDIA DGX B300 (2304 GB)
Each dot is a model at the best quant that fits ≤2 TB. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.
Full ≤2 TB ranking →Benchmarks
The 6 boards that weigh most in the llmrun Score, of 43 with a result for this model; badges show who ran the test.
- GPQA Diamond
Epoch AI · Jul 2026Independent
Independent93.1%
#2/100 open
- LMArena Text
LMArena · Nov 2026Arena
Arena1487.4
#1/191 open
- LiveBench Coding
LiveBench · Jun 2026Independent
Independent81.5
#1/20 open
- LiveBench Reasoning
LiveBench · Jun 2026Independent
Independent90.7
#1/20 open
- AIME 2024/2025
Epoch AI · Jul 2026Independent
Independent97.2%
#6/88 open
- FrontierMath
Epoch AI · Jul 2026Independent
Independent72.2%
#1/19 open
In the ≤2 TB class
107 models fit ≤2 TBSame Score, only models that fit ≤2 TB at their best quant: this model's peers by memory need.
- #1
Kimi K3.1 ProMoonshot AI
139.8
1712.1 GB
- #2
Inkling 2 SmallThinking Machines
134.7
359.1 GB
- #3
DeepSeek V4.1 Flash 1017DeepSeek
134.5
458.4 GB
- #4
MiMo V2.6 Pro RLXiaomi
133.5
614.1 GB
- #6
MiMo V2.6 Flash RLXiaomi
131.9
186.5 GB
Alternatives to Kimi K3
Kimi K3 family · 3 models →Official models with an llmrun Score, each answering one question; sizes are each model's default quant (usually Q4_K_M) with a 16K-token context.
Best alternative at this size
Kimi K3.1 Pro
Moonshot AI
- 7 higher Score
- 42 GB more VRAM
Score 139.8 · 1712.1 GB
Fits in less VRAM
Inkling 2 Small
Thinking Machines
- 1.9 higher Score
- 1310.9 GB less VRAM
Score 134.7 · 359.1 GB
Other vendor
DeepSeek V4 Pro 0813
DeepSeek
- 3.6 lower Score
- 679.2 GB less VRAM
Score 129.2 · 990.8 GB
Similar models
4| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017DeepSeek | 134.5 | 458.4 GB | —needs > 24 GB | similar score |
| MiMo V2.6 Pro RLXiaomi | 133.5 | 614.1 GB | —needs > 24 GB | similar score |
| MiMo V2.6 Flash RLXiaomi | 131.9 | 186.5 GB | —needs > 24 GB | similar score |
| DeepSeek V4 ProDeepSeek | 116.7 | 959.8 GB | —needs > 24 GB | smaller |
Specifications
- Publisher
- Moonshot AI
- Family
- Kimi K3
- Parameters
- 2779.9B
- Active parameters
- 106B per token
- Architecture
- KimiK3ForConditionalGeneration
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 163,840
- Release Date
- 2026-06-13
- License
- Other
Frequently Asked Questions
How much VRAM does Kimi K3 need?
Kimi K3 requires 1673.7 GB of VRAM at Q4_K_M, or 5565.6 GB at BF16. Full 1049K context adds up to 106.9 GB (1780.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2779.9B × 4.8 bits ÷ 8 = 1668 GB
KV Cache + Overhead ≈ 5.7 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 112.6 GB (at full 1049K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Kimi K3?
No — Kimi K3 requires at least 770.2 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for Kimi K3?
For Kimi K3, Q4_K_M (1673.7 GB) offers the best balance of quality and VRAM usage. Q5_K_M (1986.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 770.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Kimi K3 on a Mac?
Kimi K3 requires at least 770.2 GB at IQ2_XXS. None of the 159 Macs we list has that much usable memory (the largest has 508.5 GB after macOS overhead).
Can I run Kimi K3 locally?
Yes — Kimi K3 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of Kimi K3?
At Q4_K_M, the download is about 1667.96 GB. The full-precision BF16 version is 5559.86 GB. The smallest option (IQ2_XXS) is 764.48 GB.
Which GPUs can run Kimi K3?
No single consumer GPU has enough VRAM to run Kimi K3 at Q4_K_M (1673.7 GB). Multi-GPU or professional hardware is required.
Which devices can run Kimi K3?
Kimi K3 requires at least 1673.7 GB at Q4_K_M, which exceeds the usable memory of every unified-memory device we list (the largest has 508.5 GB).