llmrun

Kimi K2.5 vs GLM 5

Kimi K2.5 leads llmrun Score 113.9 to 111.8 (ranges overlap); neither fits 24 GB.

Run Kimi K2.5 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 · Z.ai

GLM 5
111.8llmrun Score

753.9B · 42.4B active · 198K context · MIT · Feb 2026

ChatFunctions

Which should you choose?

Choose Kimi K2.5 if you want…

  • Higher llmrun Score

    113.9 vs 111.8, ranges overlap

  • Also does vision

    GLM 5 doesn't list it

Choose GLM 5 if you want…

  • Stronger at agents

    117.9 vs 110.4

  • Lighter on memory

    456.5 vs 620.0 GB at Q4_K_M

  • Also does chat

    Kimi K2.5 doesn't list it

  • More permissive license

    MIT vs Other

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

GLM 5

Doesn't fit

smallest quant needs 209.1 GB

12 GB

RTX 3060 12GB · 12 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

GLM 5

Doesn't fit

smallest quant needs 209.1 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

GLM 5

Doesn't fit

smallest quant needs 209.1 GB

24 GBreference

RTX 4090 · 24 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

GLM 5

Doesn't fit

smallest quant needs 209.1 GB

32 GB

RTX 5090 · 32 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

GLM 5

Doesn't fit

smallest quant needs 209.1 GB

48 GB

RTX A6000 · 48 GB tier

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

GLM 5

Doesn't fit

smallest quant needs 209.1 GB

Mac 32 GB

Mac Mini M4 · Macs

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

GLM 5

Doesn't fit

smallest quant needs 209.1 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

GLM 5

Doesn't fit

smallest quant needs 209.1 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Kimi K2.5

Doesn't fit

smallest quant needs 283.8 GB

GLM 5

Doesn't fit

smallest quant needs 209.1 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

GLM 5

111.8109–115

Coding

Kimi K2.5

110.4103–118

GLM 5

110.2102–118

Agents

Kimi K2.5

110.4104–117

GLM 5

117.9112–124

Science

Kimi K2.5

116.7107–126

GLM 5

no data

Reasoning

Kimi K2.5

114.7111–118

GLM 5

109.7106–114

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

GLM 5 · #29 of 106 open models · #25 of 102 that fit ≤512 GB

Benchmarks

13 shared boards: Kimi K2.5 leads 6, GLM 5 leads 6 · Benchmarks imported Nov 2026

SWE-bench Verified

Kimi K2.5

70.8%#4/20 open

IndependentSWE-bench · Feb 2026

GLM 5

72.8%#2/20 open

IndependentSWE-bench · Feb 2026

GPQA Diamond

Kimi K2.5

87.6%#19/100 open

IndependentEpoch AI · Jan 2026

GLM 5

87.8%#18/100 open

IndependentEpoch AI · Feb 2026

AIME 2024/2025

Kimi K2.5

92.2%#13/88 open

IndependentEpoch AI · Jan 2026

GLM 5

80.0%#27/88 open

IndependentEpoch AI · Feb 2026

Terminal-Bench

Kimi K2.5

43.2%#3/16 open

Lab-reportedEpoch AI · Jan 2026

GLM 5

52.4%#1/16 open

Lab-reportedEpoch AI · Feb 2026

ARC-AGI-2

Kimi K2.5

11.8%#13/22 open

IndependentEpoch AI · Jan 2026

GLM 5

4.9%#15/22 open

IndependentEpoch AI · Feb 2026

MMLU-Pro

Kimi K2.5

87.1%#3/146 open

IndependentTIGER-Lab

GLM 5

86.0%#6/146 open

IndependentTIGER-Lab

SWE-bench Multilingual

Kimi K2.5

67.3%#3/4 open

IndependentSWE-bench · Feb 2026

GLM 5

69.7%#1/4 open

IndependentSWE-bench · Feb 2026

ARC-AGI

Kimi K2.5

65.3%#13/22 open

IndependentEpoch AI · Jan 2026

GLM 5

44.7%#16/22 open

IndependentEpoch AI · Feb 2026

SimpleBench

Kimi K2.5

46.8%#10/25 open

IndependentEpoch AI · Jan 2026

GLM 5

53.2%#6/25 open

IndependentEpoch AI · Feb 2026

WeirdML

Kimi K2.5

45.6%#15/47 open

IndependentEpoch AI · Jan 2026

GLM 5

48.2%#12/47 open

IndependentEpoch AI · Feb 2026

12 more boards (other shared and single-model boards)
ALE-Bench

Kimi K2.5

821.6#21/48 open

Lab-reportedEpoch AI · Jan 2026

GLM 5

765.6#23/48 open

Lab-reportedEpoch AI · Feb 2026

CL-bench

Kimi K2.5

19.3%#1/7 open

Lab-reportedEpoch AI · Jan 2026

GLM 5

18.7%#2/7 open

Lab-reportedEpoch AI · Feb 2026

Vending-Bench 2

Kimi K2.5

1198.5#11/17 open

Lab-reportedEpoch AI · Jan 2026

GLM 5

4432.1#7/17 open

Lab-reportedEpoch AI · Feb 2026

LMArena Text

Kimi K2.5

1449.7#15/188 open

ArenaLMArena · Oct 2026

GLM 5

1457.2#12/188 open

ArenaLMArena · Oct 2026

LMArena WebDev

Kimi K2.5

1436.2#24/55 open

ArenaLMArena · Oct 2026

GLM 5

1435.6#26/55 open

ArenaLMArena · Oct 2026

Only GLM 5 (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.

Q2_K

Kimi K2.5

440 GB373.8 GB file

32K 439 GB · 128K 446 GB

GLM 5

325 GB276.0 GB file

32K 324 GB · 128K 332 GB

Q3_K_S

Kimi K2.5

453 GB443.2 GB file

32K 452 GB · 128K 459 GB

GLM 5

334 GB326.3 GB file

32K 333 GB · 128K 342 GB

Q3_K_M

Kimi K2.5

504 GB489.8 GB file

32K 503 GB · 128K 510 GB

GLM 5

372 GB360.3 GB file

32K 371 GB · 128K 380 GB

Q4_0

Kimi K2.5

517 GB581.2 GB file

32K 516 GB · 128K 523 GB

GLM 5

381 GB427.1 GB file

32K 380 GB · 128K 389 GB

Q4_K_M

Kimi K2.5

620 GB621.2 GB file

32K 619 GB · 128K 626 GB

GLM 5

457 GB455.9 GB file

32K 456 GB · 128K 464 GB

Q5_K_M

Kimi K2.5

736 GB728.7 GB file

32K 734 GB · 128K 741 GB

GLM 5

541 GB535.2 GB file

32K 540 GB · 128K 549 GB

Q6_K

Kimi K2.5

851 GB842.9 GB file

32K 850 GB · 128K 857 GB

GLM 5

626 GB619.4 GB file

32K 625 GB · 128K 634 GB

Q8_0

Kimi K2.5

1031 GB1091.1 GB file

32K 1029 GB · 128K 1036 GB

GLM 5

758 GB801.3 GB file

32K 757 GB · 128K 766 GB

16 more quants

IQ2_XXS

Kimi K2.5

286 GB326.7 GB file

32K 285 GB · 128K 292 GB

GLM 5

212 GB241.1 GB file

32K 211 GB · 128K 219 GB

IQ2_XS

Kimi K2.5

312 GB283.1 GB file

32K 311 GB · 128K 318 GB

GLM 5

not listed

IQ2_S

Kimi K2.5

325 GB283.8 GB file

32K 324 GB · 128K 330 GB

GLM 5

not listed

IQ2_M

Kimi K2.5

350 GB345.2 GB file

32K 349 GB · 128K 356 GB

GLM 5

259 GB254.8 GB file

32K 258 GB · 128K 267 GB

IQ3_XXS

Kimi K2.5

402 GB414.8 GB file

32K 401 GB · 128K 407 GB

GLM 5

296 GB304.5 GB file

32K 295 GB · 128K 304 GB

IQ3_XS

Kimi K2.5

427 GB420.1 GB file

32K 426 GB · 128K 433 GB

GLM 5

not listed

IQ3_S

Kimi K2.5

440 GB405.3 GB file

32K 439 GB · 128K 446 GB

GLM 5

not listed

IQ3_M

Kimi K2.5

466 GB466.9 GB file

32K 465 GB · 128K 472 GB

GLM 5

not listed

Q3_K_L

Kimi K2.5

530 GB487.5 GB file

32K 529 GB · 128K 536 GB

GLM 5

not listed

IQ4_XS

Kimi K2.5

556 GB547.2 GB file

32K 555 GB · 128K 561 GB

GLM 5

409 GB402.9 GB file

32K 408 GB · 128K 417 GB

IQ4_NL

Kimi K2.5

582 GB579.1 GB file

32K 580 GB · 128K 587 GB

GLM 5

428 GB425.9 GB file

32K 427 GB · 128K 436 GB

Q4_1

Kimi K2.5

582 GB642.9 GB file

32K 580 GB · 128K 587 GB

GLM 5

428 GB472.7 GB file

32K 427 GB · 128K 436 GB

Q4_K_S

Kimi K2.5

582 GB583.3 GB file

32K 580 GB · 128K 587 GB

GLM 5

428 GB428.4 GB file

32K 427 GB · 128K 436 GB

Q4_K_L

Kimi K2.5

633 GB581.2 GB file

32K 632 GB · 128K 638 GB

GLM 5

not listed

Q5_K_S

Kimi K2.5

710 GB707.0 GB file

32K 709 GB · 128K 715 GB

GLM 5

523 GB519.7 GB file

32K 522 GB · 128K 530 GB

BF16

Kimi K2.5

2058 GB2053.2 GB file

32K 2056 GB · 128K 2063 GB

GLM 5

1512 GB1508.0 GB file

32K 1511 GB · 128K 1520 GB

How to run each

Specifications

Specifications of Kimi K2.5 and GLM 5
SpecKimi K2.5GLM 5
PublisherMoonshot AIZ.ai
Parameters1026.9B753.9B
Active parameters33B per token42B per token
ArchitectureKimiK25ForConditionalGenerationGlmMoeDsaForCausalLM
Context256K tokens198K tokens
ModalitiesVision, Function-callingChat, Function-calling
LicenseOtherMIT
ReleasedJan 2026Feb 2026

Frequently Asked Questions

Which is better, Kimi K2.5 or GLM 5?

Kimi K2.5 leads llmrun Score 113.9 to 111.8 (ranges overlap); neither fits 24 GB. Choose Kimi K2.5 for higher llmrun Score and also does vision; choose GLM 5 for stronger at agents and lighter on memory.

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

At Q4_K_M, Kimi K2.5 requires 620.0 GB while GLM 5 needs 456.5 GB, making GLM 5 the easier model to run on your local setup.

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

Kimi K2.5 does not fit (smallest quant needs 283.8 GB); GLM 5 does not fit (smallest quant needs 209.1 GB).

Which has a longer context window, Kimi K2.5 or GLM 5?

Kimi K2.5 supports 262,144 tokens and GLM 5 supports 202,752 tokens.

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