llmrun

Kimi K2.5 vs Inkling

Kimi K2.5 and Inkling match in llmrun Score, with values of 113.9 versus 115.8; neither fits 24 GB.

Run Inkling in the cloud →

Model A · Moonshot AI

Kimi K2.5
113.9llmrun Score

1026.9B · 33.3B active · 256K context · Other · Jan 2026

VisionFunctions

Model B · Thinking Machines

Inkling
115.8llmrun Score

952.4B · 18.1B active · Apache 2.0 · Jul 2026

VisionChat

Which should you choose?

Choose Kimi K2.5 if you want…

  • Also does function-calling

    Inkling doesn't list it

Choose Inkling if you want…

  • Stronger at reasoning

    121.0 vs 114.7

  • Ahead on the benchmarks

    7 of 10 shared boards

  • Also does chat

    Kimi K2.5 doesn't list it

  • More permissive license

    Apache 2.0 vs Other

  • Newer release

    Jul 2026 vs Jan 2026

On your hardware

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

8 GB

RTX 4060 · 8 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

Inkling

Doesn't fit

smallest quant needs 408.4 GB

12 GB

RTX 3060 12GB · 12 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

Inkling

Doesn't fit

smallest quant needs 408.4 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

Inkling

Doesn't fit

smallest quant needs 408.4 GB

24 GBreference

RTX 4090 · 24 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

Inkling

Doesn't fit

smallest quant needs 408.4 GB

32 GB

RTX 5090 · 32 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

Inkling

Doesn't fit

smallest quant needs 408.4 GB

48 GB

RTX A6000 · 48 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

Inkling

Doesn't fit

smallest quant needs 408.4 GB

Mac 32 GB

Mac Mini M4 · Macs

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

Inkling

Doesn't fit

smallest quant needs 408.4 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

Inkling

Doesn't fit

smallest quant needs 408.4 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

Inkling

Doesn't fit

smallest quant needs 408.4 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

Overall

Kimi K2.5

113.9111–117

Inkling

115.8114–118

Coding

Kimi K2.5

110.4103–118

Inkling

109.4104–115

Agents

Kimi K2.5

110.4104–117

Inkling

110.9101–120

Math

Kimi K2.5

no data

Inkling

112.1107–117

Science

Kimi K2.5

116.7107–126

Inkling

116.3106–127

Reasoning

Kimi K2.5

114.7111–118

Inkling

121.0118–124

Kimi K2.5 · #25 of 106 open models · #21 of 102 that fit ≤640 GB

Inkling · #23 of 106 open models · #19 of 102 that fit ≤640 GB

Benchmarks

10 shared boards: Kimi K2.5 leads 3, Inkling leads 7 · Benchmarks imported Nov 2026

GPQA Diamond

Kimi K2.5

87.6%#19/100 open

IndependentEpoch AI · Jan 2026

Inkling

88.3%#16/100 open

IndependentEpoch AI · Jul 2026

AIME 2024/2025

Kimi K2.5

92.2%#13/88 open

IndependentEpoch AI · Jan 2026

Inkling

88.9%#19/88 open

IndependentEpoch AI · Jul 2026

ARC-AGI-2

Kimi K2.5

11.8%#13/22 open

IndependentEpoch AI · Jan 2026

Inkling

36.5%#10/22 open

IndependentEpoch AI · Jul 2026

SciCode

Kimi K2.5

49.0%#20/72 open

Lab-reportedEpoch AI · Jan 2026

Inkling

47.0%#23/72 open

Lab-reportedEpoch AI · Jul 2026

ARC-AGI

Kimi K2.5

65.3%#13/22 open

IndependentEpoch AI · Jan 2026

Inkling

79.5%#10/22 open

IndependentEpoch AI · Jul 2026

SimpleQA

Kimi K2.5

34.3%#12/19 open

IndependentEpoch AI · Jan 2026

Inkling

40.3%#9/19 open

IndependentEpoch AI · Jul 2026

SimpleBench

Kimi K2.5

46.8%#10/25 open

IndependentEpoch AI · Jan 2026

Inkling

50.0%#8/25 open

IndependentEpoch AI · Jul 2026

WeirdML

Kimi K2.5

45.6%#15/47 open

IndependentEpoch AI · Jan 2026

Inkling

32.3%#38/47 open

IndependentEpoch AI · Jul 2026

ALE-Bench

Kimi K2.5

821.6#21/48 open

Lab-reportedEpoch AI · Jan 2026

Inkling

946.0#15/48 open

Lab-reportedEpoch AI · Jul 2026

CritPt

Kimi K2.5

3.1%#27/84 open

Lab-reportedEpoch AI · Jan 2026

Inkling

5.4%#21/84 open

Lab-reportedEpoch AI · Jul 2026

31 more boards (other shared and single-model boards)
LMArena Text

Kimi K2.5

1449.7#15/188 open

ArenaLMArena · Oct 2026

Inkling

1442.2#17/188 open

ArenaLMArena · Oct 2026

LMArena WebDev

Kimi K2.5

1436.2#24/55 open

ArenaLMArena · Oct 2026

Inkling

1415.2#28/55 open

ArenaLMArena · Oct 2026

VRAM by quantization

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

Q2_K

Kimi K2.5

440 GB373.8 GB file

32K 439 GB · 128K 446 GB

Inkling

405 GB~404.8 GB file

32K 412 GB · 128K 432 GB

Q3_K_S

Kimi K2.5

453 GB443.2 GB file

32K 452 GB · 128K 459 GB

Inkling

not listed

Q3_K_M

Kimi K2.5

504 GB489.8 GB file

32K 503 GB · 128K 510 GB

Inkling

465 GB~464.3 GB file

32K 471 GB · 128K 491 GB

Q4_0

Kimi K2.5

517 GB581.2 GB file

32K 516 GB · 128K 523 GB

Inkling

not listed

Q4_K_M

Kimi K2.5

620 GB621.2 GB file

32K 619 GB · 128K 626 GB

Inkling

572 GB~571.4 GB file

32K 578 GB · 128K 598 GB

Q5_K_M

Kimi K2.5

736 GB728.7 GB file

32K 734 GB · 128K 741 GB

Inkling

679 GB~678.6 GB file

32K 686 GB · 128K 705 GB

Q6_K

Kimi K2.5

851 GB842.9 GB file

32K 850 GB · 128K 857 GB

Inkling

786 GB~785.7 GB file

32K 793 GB · 128K 813 GB

Q8_0

Kimi K2.5

1031 GB1091.1 GB file

32K 1029 GB · 128K 1036 GB

Inkling

953 GB856.8 GB file

32K 959 GB · 128K 979 GB

16 more quants

IQ2_XXS

Kimi K2.5

286 GB326.7 GB file

32K 285 GB · 128K 292 GB

Inkling

not listed

IQ2_XS

Kimi K2.5

312 GB283.1 GB file

32K 311 GB · 128K 318 GB

Inkling

not listed

IQ2_S

Kimi K2.5

325 GB283.8 GB file

32K 324 GB · 128K 330 GB

Inkling

not listed

IQ2_M

Kimi K2.5

350 GB345.2 GB file

32K 349 GB · 128K 356 GB

Inkling

not listed

IQ3_XXS

Kimi K2.5

402 GB414.8 GB file

32K 401 GB · 128K 407 GB

Inkling

not listed

IQ3_XS

Kimi K2.5

427 GB420.1 GB file

32K 426 GB · 128K 433 GB

Inkling

not listed

IQ3_S

Kimi K2.5

440 GB405.3 GB file

32K 439 GB · 128K 446 GB

Inkling

not listed

IQ3_M

Kimi K2.5

466 GB466.9 GB file

32K 465 GB · 128K 472 GB

Inkling

not listed

Q3_K_L

Kimi K2.5

530 GB487.5 GB file

32K 529 GB · 128K 536 GB

Inkling

not listed

IQ4_XS

Kimi K2.5

556 GB547.2 GB file

32K 555 GB · 128K 561 GB

Inkling

not listed

IQ4_NL

Kimi K2.5

582 GB579.1 GB file

32K 580 GB · 128K 587 GB

Inkling

not listed

Q4_1

Kimi K2.5

582 GB642.9 GB file

32K 580 GB · 128K 587 GB

Inkling

not listed

Q4_K_S

Kimi K2.5

582 GB583.3 GB file

32K 580 GB · 128K 587 GB

Inkling

not listed

Q4_K_L

Kimi K2.5

633 GB581.2 GB file

32K 632 GB · 128K 638 GB

Inkling

not listed

Q5_K_S

Kimi K2.5

710 GB707.0 GB file

32K 709 GB · 128K 715 GB

Inkling

not listed

BF16

Kimi K2.5

2058 GB2053.2 GB file

32K 2056 GB · 128K 2063 GB

Inkling

1905 GB1894.3 GB file

32K 1912 GB · 128K 1932 GB

How to run each

Specifications

Specifications of Kimi K2.5 and Inkling
SpecKimi K2.5Inkling
PublisherMoonshot AIThinking Machines
Parameters1026.9B952.4B
Active parameters33B per token18B per token
ArchitectureKimiK25ForConditionalGenerationInklingForConditionalGeneration
Context256K tokens—
ModalitiesVision, Function-callingVision, Chat
LicenseOtherApache 2.0
ReleasedJan 2026Jul 2026

Frequently Asked Questions

Which is better, Kimi K2.5 or Inkling?

Kimi K2.5 and Inkling match in llmrun Score, with values of 113.9 versus 115.8; neither fits 24 GB. Choose Kimi K2.5 for also does function-calling; choose Inkling for stronger at reasoning and ahead on the benchmarks.

Which needs less VRAM, Kimi K2.5 or Inkling?

At Q4_K_M, Kimi K2.5 requires 620.0 GB while Inkling needs 572.1 GB, making Inkling the easier model to run on your local setup.

Can I run Kimi K2.5 or Inkling on a 16 GB GPU?

Kimi K2.5 does not fit (smallest quant needs 283.8 GB); Inkling does not fit (smallest quant needs 408.4 GB).

Kimi K2.5 vs Inkling — VRAM & GPU Comparison | llmrun