Kimi K2 Thinking vs Qwen3.8 27B

Qwen3.8 27B leads llmrun Score 121.5 to 108.8; only Qwen3.8 27B fits 24 GB (Q4_K_M); Kimi K2 Thinking needs 283.7 GB even at its smallest quant.

Model A · Moonshot AI

Kimi K2 Thinking

108.8llmrun Score

1026.4B · 32.9B active · 256K context · Other · Nov 2025

ChatFunctions

Model B · Alibaba

Qwen3.8 27B

121.5llmrun Score

27.8B · 256K context · Apache 2.0 · Aug 2026

VisionFunctions

Which should you choose?

Choose Kimi K2 Thinking if you want…

Also does chat
Qwen3.8 27B doesn't list it

Choose Qwen3.8 27B if you want…

Higher llmrun Score
121.5 vs 108.8
Stronger at coding
112.1 vs 103.3
Fits a 12 GB GPU
IQ3_XXS · 12 GB; Kimi K2 Thinking needs 283.7 GB at its smallest quant
Fits a Mac 32 GB
Q4_K_M · 17.9 GB; Kimi K2 Thinking needs 283.7 GB at its smallest quant
Lighter on memory
17.4 vs 619.7 GB at Q4_K_M
Also does vision
Kimi K2 Thinking doesn't list it

On your hardware

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

MemoryKimi K2 ThinkingQwen3.8 27B

8 GB

RTX 4060 · 8 GB tier

Kimi K2 Thinking

Doesn't fit

smallest quant needs 283.7 GB

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

Kimi K2 Thinking

Doesn't fit

smallest quant needs 283.7 GB

Qwen3.8 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16Kfits

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Kimi K2 Thinking

Doesn't fit

smallest quant needs 283.7 GB

Qwen3.8 27B

Q3_K_L · ~19 tok/s

15.4 GB · up to 16Kfits

24 GBreference

RTX 4090 · 24 GB tier

Kimi K2 Thinking

Doesn't fit

smallest quant needs 283.7 GB

Qwen3.8 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64Kfits

32 GB

RTX 5090 · 32 GB tier

Kimi K2 Thinking

Doesn't fit

smallest quant needs 283.7 GB

Qwen3.8 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256Kfits

48 GB

RTX A6000 · 48 GB tier

Kimi K2 Thinking

Doesn't fit

smallest quant needs 283.7 GB

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kfits

Mac 32 GB

Mac Mini M4 · Macs

Kimi K2 Thinking

Doesn't fit

smallest quant needs 283.7 GB

Qwen3.8 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128Kfits

Mac 64 GB

Mac Studio M4 Max · Macs

Kimi K2 Thinking

Doesn't fit

smallest quant needs 283.7 GB

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfits

Mac 128 GB

Mac Studio M4 Max · Macs

Kimi K2 Thinking

Doesn't fit

smallest quant needs 283.7 GB

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfits

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 Thinking Qwen3.8 27B

Overall

Kimi K2 Thinking

108.8105–112

Qwen3.8 27B

121.5119–124

Coding

Kimi K2 Thinking

103.394–112

Qwen3.8 27B

112.1105–119

Agents

Kimi K2 Thinking

107.8103–113

Qwen3.8 27B

no data

Math

Kimi K2 Thinking

no data

Qwen3.8 27B

117.5111–125

Science

Kimi K2 Thinking

no data

Qwen3.8 27B

112.093–131

Reasoning

Kimi K2 Thinking

no data

Qwen3.8 27B

124.1121–127

Kimi K2 Thinking · #28 of 92 open models · #25 of 88 that fit ≤640 GB

Qwen3.8 27B · #10 of 92 open models · #1 of 34 that fit 24 GB

Benchmarks

2 shared boards: Kimi K2 Thinking leads 0, Qwen3.8 27B leads 2 · Benchmarks imported Oct 2026

BoardKimi K2 ThinkingQwen3.8 27B

LMArena Text

Kimi K2 Thinking

1430.1#25/186 open

ArenaLMArena · Oct 2026

Qwen3.8 27B

1438.1#22/186 open

ArenaLMArena · Oct 2026

LMArena WebDev

Kimi K2 Thinking

1322.1#40/50 open

ArenaLMArena · Oct 2026

Qwen3.8 27B

1592.8#10/50 open

ArenaLMArena · Oct 2026

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

Only Kimi K2 Thinking (9)

Only Qwen3.8 27B (12)

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 ThinkingQwen3.8 27B

Q2_K

Kimi K2 Thinking

440 GB374.1 GB file

32K 439 GB · 128K 446 GB

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

Q3_K_S

Kimi K2 Thinking

453 GB443.2 GB file

32K 452 GB · 128K 459 GB

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

Q3_K_M

Kimi K2 Thinking

504 GB490.0 GB file

32K 503 GB · 128K 510 GB

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

Q4_0

Kimi K2 Thinking

517 GB581.2 GB file

32K 516 GB · 128K 523 GB

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

Q4_K_M

Kimi K2 Thinking

620 GB621.2 GB file

32K 618 GB · 128K 625 GB

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

Q5_K_M

Kimi K2 Thinking

735 GB728.7 GB file

32K 734 GB · 128K 741 GB

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

Q6_K

Kimi K2 Thinking

851 GB842.9 GB file

32K 849 GB · 128K 856 GB

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

Q8_0

Kimi K2 Thinking

1030 GB1091.1 GB file

32K 1029 GB · 128K 1036 GB

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

17 more quants

IQ2_XXS

Kimi K2 Thinking

286 GB335.2 GB file

32K 285 GB · 128K 292 GB

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

IQ2_XS

Kimi K2 Thinking

312 GB283.4 GB file

32K 311 GB · 128K 317 GB

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

IQ2_S

Kimi K2 Thinking

325 GB284.1 GB file

32K 323 GB · 128K 330 GB

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

IQ2_M

Kimi K2 Thinking

350 GB353.6 GB file

32K 349 GB · 128K 356 GB

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

IQ3_XXS

Kimi K2 Thinking

402 GB421.7 GB file

32K 400 GB · 128K 407 GB

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

IQ3_XS

Kimi K2 Thinking

427 GB420.7 GB file

32K 426 GB · 128K 433 GB

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

IQ3_S

Kimi K2 Thinking

not listed

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

IQ3_M

Kimi K2 Thinking

466 GB467.5 GB file

32K 464 GB · 128K 471 GB

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

Q3_K_L

Kimi K2 Thinking

530 GB487.7 GB file

32K 529 GB · 128K 536 GB

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

IQ4_XS

Kimi K2 Thinking

556 GB547.2 GB file

32K 554 GB · 128K 561 GB

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

IQ4_NL

Kimi K2 Thinking

581 GB579.1 GB file

32K 580 GB · 128K 587 GB

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_1

Kimi K2 Thinking

581 GB642.9 GB file

32K 580 GB · 128K 587 GB

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_S

Kimi K2 Thinking

581 GB583.3 GB file

32K 580 GB · 128K 587 GB

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_L

Kimi K2 Thinking

not listed

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

Q5_K_S

Kimi K2 Thinking

710 GB707.0 GB file

32K 708 GB · 128K 715 GB

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

Q5_K_L

Kimi K2 Thinking

not listed

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

BF16

Kimi K2 Thinking

2057 GB2053.2 GB file

32K 2055 GB · 128K 2062 GB

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

How to run each

Kimi K2 Thinking

Ollama · Q4_K_M

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

All ways to run Kimi K2 Thinking →

Qwen3.8 27B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3.8-27B-GGUF:Q4_K_M

All ways to run Qwen3.8 27B →

Specifications

Specifications of Kimi K2 Thinking and Qwen3.8 27B
Spec	Kimi K2 Thinking	Qwen3.8 27B
Publisher	Moonshot AI	Alibaba
Parameters	1026.4B	27.8B
Active parameters	33B per token	—
Architecture	DeepseekV3ForCausalLM	Qwen3_5ForConditionalGeneration
Context	256K tokens	256K tokens
Modalities	Chat, Function-calling	Vision, Function-calling
License	Other	Apache 2.0
Released	Nov 2025	Aug 2026

Frequently Asked Questions

Which is better, Kimi K2 Thinking or Qwen3.8 27B?

Qwen3.8 27B leads llmrun Score 121.5 to 108.8; only Qwen3.8 27B fits 24 GB (Q4_K_M); Kimi K2 Thinking needs 283.7 GB even at its smallest quant. Choose Kimi K2 Thinking for also does chat; choose Qwen3.8 27B for higher llmrun Score and stronger at coding.

Which needs less VRAM, Kimi K2 Thinking or Qwen3.8 27B?

At Q4_K_M, Kimi K2 Thinking requires 619.7 GB while Qwen3.8 27B needs 17.4 GB, making Qwen3.8 27B the easier model to run on your local setup.

Can I run Kimi K2 Thinking or Qwen3.8 27B on a 16 GB GPU?

Kimi K2 Thinking does not fit (smallest quant needs 283.7 GB); Qwen3.8 27B fits at Q3_K_L.

Which has a longer context window, Kimi K2 Thinking or Qwen3.8 27B?

Kimi K2 Thinking supports 262,144 tokens and Qwen3.8 27B supports 262,144 tokens.