llmrun

DeepSeek R1 0528 vs Kimi K2 Instruct 0905

DeepSeek R1 0528 and Kimi K2 Instruct 0905 match in llmrun Score, with values of 103.7 versus 102.4; neither fits 24 GB.

Model A · DeepSeek

DeepSeek R1 0528
103.7llmrun Score

684.5B · 40.1B active · 160K context · MIT · May 2025

ChatReasoningFunctions

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 DeepSeek R1 0528 if you want…

  • Stronger at coding

    107.3 vs 100.0

  • Ahead on the benchmarks

    2 of 3 shared boards

  • Lighter on memory

    414.6 vs 619.8 GB at Q4_K_M

  • Also does reasoning

    Kimi K2 Instruct 0905 doesn't list it

  • More permissive license

    MIT vs Other

Choose Kimi K2 Instruct 0905 if you want…

  • Longer context window

    256K vs 160K tokens

  • Newer release

    Sep 2025 vs May 2025

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

DeepSeek R1 0528

Doesn't fit

smallest quant needs 189.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

12 GB

RTX 3060 12GB · 12 GB tier

DeepSeek R1 0528

Doesn't fit

smallest quant needs 189.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

DeepSeek R1 0528

Doesn't fit

smallest quant needs 189.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

24 GBreference

RTX 4090 · 24 GB tier

DeepSeek R1 0528

Doesn't fit

smallest quant needs 189.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

32 GB

RTX 5090 · 32 GB tier

DeepSeek R1 0528

Doesn't fit

smallest quant needs 189.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

48 GB

RTX A6000 · 48 GB tier

DeepSeek R1 0528

Doesn't fit

smallest quant needs 189.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

Mac 32 GB

Mac Mini M4 · Macs

DeepSeek R1 0528

Doesn't fit

smallest quant needs 189.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

Mac 64 GB

Mac Studio M4 Max · Macs

DeepSeek R1 0528

Doesn't fit

smallest quant needs 189.7 GB

Kimi K2 Instruct 0905

Doesn't fit

smallest quant needs 283.7 GB

Mac 128 GB

Mac Studio M4 Max · Macs

DeepSeek R1 0528

Doesn't fit

smallest quant needs 189.7 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

Overall

DeepSeek R1 0528

103.7101–106

Kimi K2 Instruct 0905

102.498–106

Coding

DeepSeek R1 0528

107.3102–113

Kimi K2 Instruct 0905

100.095–105

Reasoning

DeepSeek R1 0528

100.094–106

Kimi K2 Instruct 0905

no data

DeepSeek R1 0528 · #40 of 92 open models · #37 of 88 that fit ≤512 GB

Kimi K2 Instruct 0905 · #43 of 92 open models · #40 of 88 that fit ≤640 GB

Benchmarks

3 shared boards: DeepSeek R1 0528 leads 2, Kimi K2 Instruct 0905 leads 0 · Benchmarks imported Oct 2026

LMArena Text

DeepSeek R1 0528

1421.4#33/186 open

ArenaLMArena · Oct 2026

Kimi K2 Instruct 0905

1418.5#34/186 open

ArenaLMArena · Oct 2026

Aider Polyglot

DeepSeek R1 0528

71.4%#2/18 open

IndependentEpoch AI · May 2025

Kimi K2 Instruct 0905

59.1%#6/18 open

IndependentEpoch AI · Sep 2025

WeirdML

DeepSeek R1 0528

41.6%#18/46 open

IndependentEpoch AI · May 2025

Kimi K2 Instruct 0905

36.7%#31/46 open

IndependentEpoch AI · Sep 2025

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

DeepSeek R1 0528

804.1#17/42 open

Lab-reportedEpoch AI · May 2025

Kimi K2 Instruct 0905

267.1#39/42 open

Lab-reportedEpoch AI · Sep 2025

Fiction.LiveBench

DeepSeek R1 0528

75.0%#4/25 open

IndependentEpoch AI · May 2025

Kimi K2 Instruct 0905

66.7%#10/25 open

IndependentEpoch AI · Sep 2025

Only DeepSeek R1 0528 (7)

Only Kimi K2 Instruct 0905 (2)

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

DeepSeek R1 0528

295 GB237.8 GB file

32K 294 GB · 128K 300 GB

Kimi K2 Instruct 0905

440 GB374.1 GB file

32K 439 GB · 128K 446 GB

Q3_K_S

DeepSeek R1 0528

303 GB293.4 GB file

32K 302 GB · 128K 309 GB

Kimi K2 Instruct 0905

453 GB443.2 GB file

32K 452 GB · 128K 459 GB

Q3_K_M

DeepSeek R1 0528

338 GB307.9 GB file

32K 336 GB · 128K 343 GB

Kimi K2 Instruct 0905

504 GB490.0 GB file

32K 503 GB · 128K 510 GB

Q4_0

DeepSeek R1 0528

346 GB386.4 GB file

32K 345 GB · 128K 352 GB

Kimi K2 Instruct 0905

517 GB581.2 GB file

32K 516 GB · 128K 523 GB

Q4_K_M

DeepSeek R1 0528

415 GB409.2 GB file

32K 413 GB · 128K 420 GB

Kimi K2 Instruct 0905

620 GB621.2 GB file

32K 618 GB · 128K 625 GB

Q5_K_M

DeepSeek R1 0528

492 GB478.3 GB file

32K 490 GB · 128K 497 GB

Kimi K2 Instruct 0905

735 GB728.7 GB file

32K 734 GB · 128K 741 GB

Q6_K

DeepSeek R1 0528

569 GB552.4 GB file

32K 567 GB · 128K 574 GB

Kimi K2 Instruct 0905

851 GB842.9 GB file

32K 849 GB · 128K 856 GB

Q8_0

DeepSeek R1 0528

688 GB713.3 GB file

32K 687 GB · 128K 694 GB

Kimi K2 Instruct 0905

1030 GB1091.1 GB file

32K 1029 GB · 128K 1036 GB

14 more quants

IQ2_XXS

DeepSeek R1 0528

192 GB164.1 GB file

32K 191 GB · 128K 198 GB

Kimi K2 Instruct 0905

286 GB330.8 GB file

32K 285 GB · 128K 292 GB

IQ2_XS

DeepSeek R1 0528

209 GB188.4 GB file

32K 208 GB · 128K 215 GB

Kimi K2 Instruct 0905

312 GB283.4 GB file

32K 311 GB · 128K 317 GB

IQ2_S

DeepSeek R1 0528

218 GB189.6 GB file

32K 217 GB · 128K 223 GB

Kimi K2 Instruct 0905

325 GB284.1 GB file

32K 323 GB · 128K 330 GB

IQ2_M

DeepSeek R1 0528

235 GB215.0 GB file

32K 234 GB · 128K 241 GB

Kimi K2 Instruct 0905

350 GB349.1 GB file

32K 349 GB · 128K 356 GB

IQ3_XXS

DeepSeek R1 0528

269 GB267.6 GB file

32K 268 GB · 128K 275 GB

Kimi K2 Instruct 0905

402 GB417.3 GB file

32K 400 GB · 128K 407 GB

IQ3_XS

DeepSeek R1 0528

286 GB277.1 GB file

32K 285 GB · 128K 292 GB

Kimi K2 Instruct 0905

427 GB420.7 GB file

32K 426 GB · 128K 433 GB

IQ3_M

DeepSeek R1 0528

312 GB307.9 GB file

32K 311 GB · 128K 318 GB

Kimi K2 Instruct 0905

466 GB467.5 GB file

32K 465 GB · 128K 471 GB

Q3_K_L

DeepSeek R1 0528

355 GB319.7 GB file

32K 353 GB · 128K 360 GB

Kimi K2 Instruct 0905

530 GB487.7 GB file

32K 529 GB · 128K 536 GB

IQ4_XS

DeepSeek R1 0528

372 GB360.0 GB file

32K 371 GB · 128K 377 GB

Kimi K2 Instruct 0905

556 GB547.2 GB file

32K 554 GB · 128K 561 GB

IQ4_NL

DeepSeek R1 0528

389 GB380.5 GB file

32K 388 GB · 128K 395 GB

Kimi K2 Instruct 0905

581 GB579.1 GB file

32K 580 GB · 128K 587 GB

Q4_1

DeepSeek R1 0528

389 GB421.0 GB file

32K 388 GB · 128K 395 GB

Kimi K2 Instruct 0905

581 GB642.9 GB file

32K 580 GB · 128K 587 GB

Q4_K_S

DeepSeek R1 0528

389 GB394.2 GB file

32K 388 GB · 128K 395 GB

Kimi K2 Instruct 0905

581 GB583.3 GB file

32K 580 GB · 128K 587 GB

Q5_K_S

DeepSeek R1 0528

475 GB463.0 GB file

32K 473 GB · 128K 480 GB

Kimi K2 Instruct 0905

710 GB707.0 GB file

32K 708 GB · 128K 715 GB

BF16

DeepSeek R1 0528

1373 GB1342.3 GB file

32K 1372 GB · 128K 1379 GB

Kimi K2 Instruct 0905

2057 GB2053.2 GB file

32K 2056 GB · 128K 2062 GB

How to run each

Specifications

Specifications of DeepSeek R1 0528 and Kimi K2 Instruct 0905
SpecDeepSeek R1 0528Kimi K2 Instruct 0905
PublisherDeepSeekMoonshot AI
Parameters684.5B1026.5B
Active parameters40B per token33B per token
ArchitectureDeepseekV3ForCausalLMDeepseekV3ForCausalLM
Context160K tokens256K tokens
ModalitiesChat, Reasoning, Function-callingChat, Function-calling
LicenseMITOther
ReleasedMay 2025Sep 2025

Frequently Asked Questions

Which is better, DeepSeek R1 0528 or Kimi K2 Instruct 0905?

DeepSeek R1 0528 and Kimi K2 Instruct 0905 match in llmrun Score, with values of 103.7 versus 102.4; neither fits 24 GB. Choose DeepSeek R1 0528 for stronger at coding and ahead on the benchmarks; choose Kimi K2 Instruct 0905 for longer context window and newer release.

Which needs less VRAM, DeepSeek R1 0528 or Kimi K2 Instruct 0905?

At Q4_K_M, DeepSeek R1 0528 requires 414.6 GB while Kimi K2 Instruct 0905 needs 619.8 GB, making DeepSeek R1 0528 the easier model to run on your local setup.

Can I run DeepSeek R1 0528 or Kimi K2 Instruct 0905 on a 16 GB GPU?

DeepSeek R1 0528 does not fit (smallest quant needs 189.7 GB); Kimi K2 Instruct 0905 does not fit (smallest quant needs 283.7 GB).

Which has a longer context window, DeepSeek R1 0528 or Kimi K2 Instruct 0905?

DeepSeek R1 0528 supports 163,840 tokens and Kimi K2 Instruct 0905 supports 262,144 tokens.

DeepSeek R1 0528 vs Kimi K2 Instruct 0905 — VRAM & GPU Comparison | llmrun