Kimi K2 Instruct vs Kimi K2 Instruct 0905

Kimi K2 Instruct 0905 leads llmrun Score 102.4 to 100.0 (ranges overlap); neither fits 24 GB.

Model A · Moonshot AI

Kimi K2 Instruct

100.0llmrun Score

1026.4B · 32.9B active · 128K context · Other · Jul 2025

ChatFunctions

Model B · Moonshot AI

Kimi K2 Instruct 0905

102.4llmrun Score

1026.5B · 32.9B active · 256K context · Other · Sep 2025

ChatFunctions

Which should you choose?

Choose Kimi K2 Instruct 0905 if you want…

Higher llmrun Score
102.4 vs 100.0, ranges overlap
Longer context window
256K vs 128K tokens

Kimi K2 Instruct: no clear edge over Kimi K2 Instruct 0905 in the data we have.

On your hardware

Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.

MemoryKimi K2 InstructKimi K2 Instruct 0905

8 GB

RTX 4060 · 8 GB tier

Kimi K2 Instruct

Doesn't fit

smallest quant needs 283.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

12 GB

RTX 3060 12GB · 12 GB tier

Kimi K2 Instruct

Doesn't fit

smallest quant needs 283.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Kimi K2 Instruct

Doesn't fit

smallest quant needs 283.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

24 GBreference

RTX 4090 · 24 GB tier

Kimi K2 Instruct

Doesn't fit

smallest quant needs 283.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

32 GB

RTX 5090 · 32 GB tier

Kimi K2 Instruct

Doesn't fit

smallest quant needs 283.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

48 GB

RTX A6000 · 48 GB tier

Kimi K2 Instruct

Doesn't fit

smallest quant needs 283.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

Mac 32 GB

Mac Mini M4 · Macs

Kimi K2 Instruct

Doesn't fit

smallest quant needs 283.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Kimi K2 Instruct

Doesn't fit

smallest quant needs 283.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Kimi K2 Instruct

Doesn't fit

smallest quant needs 283.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).

llmrun Score

with its 90% range · bars share one scale

Kimi K2 Instruct Kimi K2 Instruct 0905

Overall

Kimi K2 Instruct

100.097–103

Kimi K2 Instruct 0905

102.498–106

Coding

Kimi K2 Instruct

101.596–107

Kimi K2 Instruct 0905

100.095–105

Agents

Kimi K2 Instruct

101.697–107

Kimi K2 Instruct 0905

no data

Reasoning

Kimi K2 Instruct

89.876–104

Kimi K2 Instruct 0905

no data

Kimi K2 Instruct · #50 of 100 open models · #47 of 96 that fit ≤640 GB

Kimi K2 Instruct 0905 · #47 of 100 open models · #44 of 96 that fit ≤640 GB

Benchmarks

5 shared boards: Kimi K2 Instruct leads 2, Kimi K2 Instruct 0905 leads 2 · Benchmarks imported Oct 2026

BoardKimi K2 InstructKimi K2 Instruct 0905

SWE-bench Verified

Kimi K2 Instruct

65.4%#8/20 open

IndependentSWE-bench · Jul 2025

Kimi K2 Instruct 0905

71.2%#3/20 open

IndependentSWE-bench · Oct 2025

Aider Polyglot

Kimi K2 Instruct

59.1%#5/18 open

IndependentEpoch AI · Jul 2025

Kimi K2 Instruct 0905

59.1%#6/18 open

IndependentEpoch AI · Sep 2025

WeirdML

Kimi K2 Instruct

39.4%#25/46 open

IndependentEpoch AI · Jul 2025

Kimi K2 Instruct 0905

36.7%#31/46 open

IndependentEpoch AI · Sep 2025

Fiction.LiveBench

Kimi K2 Instruct

61.1%#13/25 open

IndependentEpoch AI · Jul 2025

Kimi K2 Instruct 0905

66.7%#10/25 open

IndependentEpoch AI · Sep 2025

ForecastBench

Kimi K2 Instruct

60.2#4/26 open

Lab-reportedEpoch AI · Jul 2025

Kimi K2 Instruct 0905

59.8#7/26 open

Lab-reportedEpoch AI · Sep 2025

7 more boards (other shared and single-model boards)

LMArena Text

Kimi K2 Instruct

1417.8#35/187 open

ArenaLMArena · Oct 2026

Kimi K2 Instruct 0905

1418.6#34/187 open

ArenaLMArena · Oct 2026

Only Kimi K2 Instruct (5)

Only Kimi K2 Instruct 0905 (1)

ALE-Bench267.1

VRAM by quantization

Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.

QuantKimi K2 InstructKimi K2 Instruct 0905

Q2_K

Kimi K2 Instruct

440 GB373.2 GB file

32K 439 GB · 128K 446 GB

Kimi K2 Instruct 0905

440 GB374.1 GB file

32K 439 GB · 128K 446 GB

Q3_K_S

Kimi K2 Instruct

453 GB442.4 GB file

32K 452 GB · 128K 459 GB

Kimi K2 Instruct 0905

453 GB443.2 GB file

32K 452 GB · 128K 459 GB

Q3_K_M

Kimi K2 Instruct

504 GB489.4 GB file

32K 503 GB · 128K 510 GB

Kimi K2 Instruct 0905

504 GB490.0 GB file

32K 503 GB · 128K 510 GB

Q4_0

Kimi K2 Instruct

517 GB580.6 GB file

32K 516 GB · 128K 523 GB

Kimi K2 Instruct 0905

517 GB581.2 GB file

32K 516 GB · 128K 523 GB

Q4_K_M

Kimi K2 Instruct

620 GB620.8 GB file

32K 618 GB · 128K 625 GB

Kimi K2 Instruct 0905

620 GB621.2 GB file

32K 618 GB · 128K 625 GB

Q5_K_M

Kimi K2 Instruct

735 GB728.3 GB file

32K 734 GB · 128K 741 GB

Kimi K2 Instruct 0905

735 GB728.7 GB file

32K 734 GB · 128K 741 GB

Q6_K

Kimi K2 Instruct

851 GB842.6 GB file

32K 849 GB · 128K 856 GB

Kimi K2 Instruct 0905

851 GB842.9 GB file

32K 849 GB · 128K 856 GB

Q8_0

Kimi K2 Instruct

1030 GB1091.1 GB file

32K 1029 GB · 128K 1036 GB

Kimi K2 Instruct 0905

1030 GB1091.1 GB file

32K 1029 GB · 128K 1036 GB

14 more quants

IQ2_XXS

Kimi K2 Instruct

286 GB328.8 GB file

32K 285 GB · 128K 292 GB

Kimi K2 Instruct 0905

286 GB330.8 GB file

32K 285 GB · 128K 292 GB

IQ2_XS

Kimi K2 Instruct

not listed

Kimi K2 Instruct 0905

312 GB283.4 GB file

32K 311 GB · 128K 317 GB

IQ2_S

Kimi K2 Instruct

not listed

Kimi K2 Instruct 0905

325 GB284.1 GB file

32K 323 GB · 128K 330 GB

IQ2_M

Kimi K2 Instruct

350 GB347.1 GB file

32K 349 GB · 128K 356 GB

Kimi K2 Instruct 0905

350 GB349.1 GB file

32K 349 GB · 128K 356 GB

IQ3_XXS

Kimi K2 Instruct

402 GB416.6 GB file

32K 400 GB · 128K 407 GB

Kimi K2 Instruct 0905

402 GB417.3 GB file

32K 400 GB · 128K 407 GB

IQ3_XS

Kimi K2 Instruct

not listed

Kimi K2 Instruct 0905

427 GB420.7 GB file

32K 426 GB · 128K 433 GB

IQ3_M

Kimi K2 Instruct

not listed

Kimi K2 Instruct 0905

466 GB467.5 GB file

32K 465 GB · 128K 471 GB

Q3_K_L

Kimi K2 Instruct

530 GB530.5 GB file

32K 529 GB · 128K 536 GB

Kimi K2 Instruct 0905

530 GB487.7 GB file

32K 529 GB · 128K 536 GB

IQ4_XS

Kimi K2 Instruct

556 GB546.5 GB file

32K 554 GB · 128K 561 GB

Kimi K2 Instruct 0905

556 GB547.2 GB file

32K 554 GB · 128K 561 GB

IQ4_NL

Kimi K2 Instruct

581 GB578.5 GB file

32K 580 GB · 128K 587 GB

Kimi K2 Instruct 0905

581 GB579.1 GB file

32K 580 GB · 128K 587 GB

Q4_1

Kimi K2 Instruct

581 GB642.5 GB file

32K 580 GB · 128K 587 GB

Kimi K2 Instruct 0905

581 GB642.9 GB file

32K 580 GB · 128K 587 GB

Q4_K_S

Kimi K2 Instruct

581 GB582.7 GB file

32K 580 GB · 128K 587 GB

Kimi K2 Instruct 0905

581 GB583.3 GB file

32K 580 GB · 128K 587 GB

Q5_K_S

Kimi K2 Instruct

710 GB706.6 GB file

32K 708 GB · 128K 715 GB

Kimi K2 Instruct 0905

710 GB707.0 GB file

32K 708 GB · 128K 715 GB

BF16

Kimi K2 Instruct

2057 GB2053.2 GB file

32K 2055 GB · 128K 2062 GB

Kimi K2 Instruct 0905

2057 GB2053.2 GB file

32K 2056 GB · 128K 2062 GB

How to run each

Kimi K2 Instruct

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Kimi-K2-Instruct-GGUF:Q4_K_M

All ways to run Kimi K2 Instruct →

Kimi K2 Instruct 0905

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Kimi-K2-Instruct-0905-GGUF:Q4_K_M

All ways to run Kimi K2 Instruct 0905 →

Specifications

Specifications of Kimi K2 Instruct and Kimi K2 Instruct 0905
Spec	Kimi K2 Instruct	Kimi K2 Instruct 0905
Publisher	Moonshot AI	Moonshot AI
Parameters	1026.4B	1026.5B
Active parameters	33B per token	33B per token
Architecture	DeepseekV3ForCausalLM	DeepseekV3ForCausalLM
Context	128K tokens	256K tokens
Modalities	Chat, Function-calling	Chat, Function-calling
License	Other	Other
Released	Jul 2025	Sep 2025

Frequently Asked Questions

Which is better, Kimi K2 Instruct or Kimi K2 Instruct 0905?

Kimi K2 Instruct 0905 leads llmrun Score 102.4 to 100.0 (ranges overlap); neither fits 24 GB. Choose Kimi K2 Instruct 0905 for higher llmrun Score and longer context window.

Which needs less VRAM, Kimi K2 Instruct or Kimi K2 Instruct 0905?

At Q4_K_M, Kimi K2 Instruct requires 619.7 GB while Kimi K2 Instruct 0905 needs 619.8 GB, making Kimi K2 Instruct the easier model to run on your local setup.

Can I run Kimi K2 Instruct or Kimi K2 Instruct 0905 on a 16 GB GPU?

Kimi K2 Instruct does not fit (smallest quant needs 283.7 GB); Kimi K2 Instruct 0905 does not fit (smallest quant needs 283.7 GB).

Which has a longer context window, Kimi K2 Instruct or Kimi K2 Instruct 0905?

Kimi K2 Instruct supports 131,072 tokens and Kimi K2 Instruct 0905 supports 262,144 tokens.