Kimi K2 Instruct 0905 — Hardware Requirements & GPU Compatibility
ChatFunctions
Kimi-K2-Instruct-0905 is Moonshot AI's updated flagship chat and agentic-coding model, a mixture-of-experts system with roughly 1.03 trillion total parameters and about 32.9 billion active per token, routed across 384 experts with 8 selected plus one shared expert per token. It is tuned for agentic coding, tool calling, and long-horizon agent workflows, using multi-head latent attention and SwiGLU activations, and Moonshot reports clear gains on coding-agent benchmarks like SWE-bench and Terminal-Bench, plus improved frontend code aesthetics, over the prior K2-Instruct-0711 release. With a trillion-parameter total footprint it needs a multi-GPU server-class setup even once quantized. Context length is 262,144 tokens, extended from 128K in the previous release. It is released under Moonshot's Modified MIT License, which is otherwise permissive but requires products with more than 100 million monthly active users or $20 million in monthly revenue to display "Kimi K2" in their interface. It was published in September 2025.
Kimi K2 Instruct 0905 runs on a multi-GPU server
Q4_K_M needs ~617.3 GB · about 5× H200 SXM 141 GB · or Mac Studio (M3 Ultra, 512GB) at Q3_K_M (~25 tok/s)
Macs from 512 GB (Q3_K_M · ~25 tok/s)
Score 102.7#51 of 106 open#47 of 102 that fit ≤640 GBOther
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
102.7
- 90% range 98.6–106.8
- #51 of 106 open models
- #47 of 102 that fit ≤640 GB
Run Kimi K2 Instruct 0905
One recommended way. 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
vllm serve moonshotai/Kimi-K2-Instruct-0905 --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Q4_K_M/Kimi-K2-Instruct-0905-Q4_K_M-00001-of-00013.gguf621.25 GB + 12 partsunsloth
Ways to runOther ways
each opens step-by-stepRun in cloud
Rent 5× H200 SXM · Q4_K_M
- Estimated hourly price
- ~$17.95/hr
- est., whole server
- GPUs
- 5 GPUs
- 705 GB of VRAM
$5+ bonus for new users
How Much VRAM Does Kimi K2 Instruct 0905 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 440.1 GB | 438.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on 7× H100 SXM 80 GB | |
| 452.9 GB | 451.7 GB | 3-bit small — 3-bit small quantization | Runs on 7× H100 SXM 80 GB | |
| 504.3 GB | 503 GB | 3-bit medium — 3-bit medium quantization | Runs on 7× H100 SXM 80 GB | |
| 517.1 GB | 515.8 GB | 4-bit · legacy — 4-bit legacy quantization | Runs on 8× H100 SXM 80 GB | |
| 619.7 GB | 618.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on 5× H200 SXM 141 GB | |
| 735.2 GB | 733.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on 6× H200 SXM 141 GB | |
| 850.7 GB | 849.4 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on 7× H200 SXM 141 GB | |
| 1030.3 GB | 1029 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on 6× B200 192 GB |
Selected Q4_K_M
4-bit medium quantization617.3GBat 16K context
- Weights
- 615.9 GB
- KV cache
- 1.2 GB
- Overhead
- 0.3 GB
Server-class: ~617.3 GB at 16K context · about 5× H200 SXM 141 GB
Which Hardware Can Run Kimi K2 Instruct 0905?
Q4_K_M · 619.7 GBKimi K2 Instruct 0905 (Q4_K_M) requires 619.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 806+ GB is recommended. Using the full 262K context window can add up to 14.8 GB, bringing total usage to 634.6 GB. No consumer GPU has enough memory.
Needs server-class hardware
Kimi K2 Instruct 0905 runs on a multi-GPU server · Q4_K_M needs ~617.3 GB
| Hardware | Quant | Memory | Speed | Context | Hardware page | |
|---|---|---|---|---|---|---|
| Mac 512 GB · Mac Studio (M3 Ultra, 512GB) | Q3_K_M | 501.8 GB | ~25 tok/s | 64K ctx | Mac Studio → | Q3_K_M · 501.8 GB · ~25 tok/s · 64K ctx |
| 8× H100 SXM 80 GB · 640 GB | IQ4_XS | 553.2 GB | — | 256K ctx | H100 SXM → | IQ4_XS · 553.2 GB · 256K ctx |
| 5× H200 SXM 141 GB · 705 GB | Q4_K_M | 617.3 GB | — | 128K ctx | H200 SXM → | Q4_K_M · 617.3 GB · 128K ctx |
| 4× B200 192 GB · 768 GB | Q4_K_M | 617.3 GB | — | 256K ctx | B200 → | Q4_K_M · 617.3 GB · 256K ctx |
Also: NVIDIA DGX A100 640GB · NVIDIA DGX H100
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 256 GB: too small for this model (needs ≥ 283.7 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
How good is Kimi K2 Instruct 0905?
The llmrun Score merges 6 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the ≤640 GB tier
- Kimi K2 Instruct 0905
- Other models
- Best Score for its VRAM
#47 of 102 that fit ≤640 GB
Each dot is a model at the best quant that fits ≤640 GB. 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 ≤640 GB ranking →Benchmarks
The 6 boards that weigh most in the llmrun Score, of 7 with a result for this model; badges show who ran the test.
- SWE-bench Verified
SWE-bench · Oct 2025Independent
Independent71.2%
#3/20 open
- LMArena Text
LMArena · Oct 2026Arena
Arena1418.5
#35/188 open
- Aider Polyglot
Epoch AI · Sep 2025Independent
Independent59.1%
#6/18 open
- WeirdML
Epoch AI · Sep 2025Independent
Independent36.7%
#32/47 open
- ALE-Bench
Epoch AI · Sep 2025Lab-reported
Lab-reported267.1
#45/48 open
- ForecastBench
Epoch AI · Sep 2025Lab-reported
Lab-reported62.7
#5/24 open
In the ≤640 GB class
102 models fit ≤640 GBSame Score, only models that fit ≤640 GB at their best quant: this model's peers by memory need.
- #1
DeepSeek V4.1 Flash 1017DeepSeek
134.4
458.4 GB
- #2
MiMo V2.6 Pro RLXiaomi
133.3
614.1 GB
- #3
MiMo V2.6 Flash RLXiaomi
131.9
186.5 GB
- #4
GLM 5.3Z.ai
130.1
453.8 GB
- #5
DeepSeek V4.1 FlashDeepSeek
129.4
458.4 GB
- #6
Step 5 PreviewStepFun
128.0
407.5 GB
Alternatives to Kimi K2 Instruct 0905
Kimi K2 family · 8 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
MiMo V2.6 Pro RL
Xiaomi
- 30.6 higher Score
- 3.2 GB less VRAM
Score 133.3 · 614.1 GB
Fits in less VRAM
DeepSeek V4.1 Flash 1017
DeepSeek
- 31.7 higher Score
- 158.9 GB less VRAM
Score 134.4 · 458.4 GB
Other vendor
GLM 5.3
Z.ai
- 27.4 higher Score
- 163.5 GB less VRAM
Score 130.1 · 453.8 GB
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| DeepSeek V4.1 FlashDeepSeek | 129.4 | 458.4 GB | —needs > 24 GB | similar score |
| DeepSeek V4 Pro 0813DeepSeek | 129.2 | 990.8 GB | —needs > 24 GB | similar score |
| Step 5 PreviewStepFun | 128.0 | 407.5 GB | —needs > 24 GB | similar score |
| Muse Spark Open 816B A42BMeta | 126.8 | 551.9 GB | —needs > 24 GB | similar score |
| GLM 5.2Z.ai | 122.9 | 453.8 GB | —needs > 24 GB | similar score |
| Kimi K2.6Moonshot AI | 120.9 | 617.6 GB | —needs > 24 GB | similar score |
| GLM 5Z.ai | 111.8 | 454.1 GB | —needs > 24 GB | similar score |
| DeepSeek V3.2DeepSeek | 110.4 | 412.7 GB | —needs > 24 GB | similar score |
| NVIDIA Nemotron 3 Ultra 550B A55B BF16NVIDIA | 109.7 | 378.4 GB | —needs > 24 GB | similar score |
| DeepSeek V3.2 ExpDeepSeek | 109.0 | 412.7 GB | —needs > 24 GB | similar score |
Specifications
- Publisher
- Moonshot AI
- Family
- Kimi K2
- Parameters
- 1026.4B
- Active parameters
- 32.9B per token
- Architecture
- DeepseekV3ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 163,840
- Release Date
- 2025-09-03
- License
- Other
Frequently Asked Questions
How much VRAM does Kimi K2 Instruct 0905 need?
Kimi K2 Instruct 0905 requires 619.7 GB of VRAM at Q4_K_M, or 2056.7 GB at BF16. Full 262K context adds up to 14.8 GB (634.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1026.4B × 4.8 bits ÷ 8 = 615.8 GB
KV Cache + Overhead ≈ 3.9 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 ≈ 18.8 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Kimi K2 Instruct 0905?
No — Kimi K2 Instruct 0905 requires at least 286.1 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for Kimi K2 Instruct 0905?
For Kimi K2 Instruct 0905, Q4_K_M (619.7 GB) offers the best balance of quality and VRAM usage. Q5_K_S (709.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 286.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Kimi K2 Instruct 0905 on a Mac?
Yes, but only at lower quantizations. The smallest Mac that can run Kimi K2 Instruct 0905 is Mac Studio (M3 Ultra, 512GB) at Q3_K_M; 1 of the 146 Macs we list can run it at some quantization. For Q4_K_M (619.7 GB) you need a Mac with more unified memory.
Can I run Kimi K2 Instruct 0905 locally?
Yes — Kimi K2 Instruct 0905 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of Kimi K2 Instruct 0905?
At Q4_K_M, the download is about 615.84 GB. The full-precision BF16 version is 2052.82 GB. The smallest option (IQ2_XXS) is 282.26 GB.
Which GPUs can run Kimi K2 Instruct 0905?
No single consumer GPU has enough VRAM to run Kimi K2 Instruct 0905 at Q4_K_M (619.7 GB). Multi-GPU or professional hardware is required.
Which devices can run Kimi K2 Instruct 0905?
Kimi K2 Instruct 0905 requires at least 619.7 GB at Q4_K_M, which exceeds the usable memory of every unified-memory device we list (the largest has 508.5 GB).