Qwen3.8 27B vs Inkling

Qwen3.8 27B leads llmrun Score 122.1 to 116.0; only Qwen3.8 27B fits 24 GB (Q4_K_M); Inkling needs 408.4 GB even at its smallest quant.

Model A · Alibaba

Qwen3.8 27B

122.1llmrun Score

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

VisionFunctions

Model B · Thinking Machines

Inkling

116.0llmrun Score

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

VisionChatFunctions

Which should you choose?

Choose Qwen3.8 27B if you want…

Higher llmrun Score
122.1 vs 116.0
Stronger at agents
122.8 vs 111.4
Stronger at coding
119.7 vs 110.2
Ahead on the benchmarks
11 of 14 shared boards
Fits a 12 GB GPU
IQ3_XXS · 12 GB; Inkling needs 408.4 GB at its smallest quant
Fits a Mac 32 GB
Q4_K_M · 17.9 GB; Inkling needs 408.4 GB at its smallest quant

Choose Inkling if you want…

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

On your hardware

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

MemoryQwen3.8 27BInkling

8 GB

RTX 4060 · 8 GB tier

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

Inkling

Doesn't fit

smallest quant needs 408.4 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3.8 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16Kfits

Inkling

Doesn't fit

smallest quant needs 408.4 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Qwen3.8 27B

Q3_K_L · ~19 tok/s

15.4 GB · up to 16Kfits

Inkling

Doesn't fit

smallest quant needs 408.4 GB

24 GBreference

RTX 4090 · 24 GB tier

Qwen3.8 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64Kfits

Inkling

Doesn't fit

smallest quant needs 408.4 GB

32 GB

RTX 5090 · 32 GB tier

Qwen3.8 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256Kfits

Inkling

Doesn't fit

smallest quant needs 408.4 GB

48 GB

RTX A6000 · 48 GB tier

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kfits

Inkling

Doesn't fit

smallest quant needs 408.4 GB

Mac 32 GB

Mac Mini M4 · Macs

Qwen3.8 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128Kfits

Inkling

Doesn't fit

smallest quant needs 408.4 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfits

Inkling

Doesn't fit

smallest quant needs 408.4 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfits

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

Qwen3.8 27B Inkling

Overall

Qwen3.8 27B

122.1120–124

Inkling

116.0114–118

Coding

Qwen3.8 27B

119.7114–125

Inkling

110.2105–115

Agents

Qwen3.8 27B

122.8117–129

Inkling

111.4102–120

Math

Qwen3.8 27B

117.5111–124

Inkling

112.1107–117

Science

Qwen3.8 27B

112.093–131

Inkling

116.4106–127

Reasoning

Qwen3.8 27B

124.0121–127

Inkling

121.0118–124

Qwen3.8 27B · #11 of 100 open models · #1 of 35 that fit 24 GB

Inkling · #18 of 100 open models · #15 of 96 that fit ≤640 GB

Benchmarks

14 shared boards: Qwen3.8 27B leads 11, Inkling leads 2 · Benchmarks imported Oct 2026

BoardQwen3.8 27BInkling

LiveBench Coding

Qwen3.8 27B

75.7#9/19 open

IndependentLiveBench · Jun 2026

Inkling

71.0#14/19 open

IndependentLiveBench · Jun 2026

LiveBench Reasoning

Qwen3.8 27B

80.0#11/19 open

IndependentLiveBench · Jun 2026

Inkling

78.3#14/19 open

IndependentLiveBench · Jun 2026

LiveBench Math

Qwen3.8 27B

86.2#11/19 open

IndependentLiveBench · Jun 2026

Inkling

88.4#7/19 open

IndependentLiveBench · Jun 2026

ARC-AGI-2

Qwen3.8 27B

42.4%#6/19 open

IndependentEpoch AI · Aug 2026

Inkling

36.5%#8/19 open

IndependentEpoch AI · Jul 2026

SciCode

Qwen3.8 27B

46.6%#19/66 open

Lab-reportedEpoch AI · Aug 2026

Inkling

47.0%#18/66 open

Lab-reportedEpoch AI · Jul 2026

ARC-AGI

Qwen3.8 27B

87.5%#6/19 open

IndependentEpoch AI · Aug 2026

Inkling

79.5%#8/19 open

IndependentEpoch AI · Jul 2026

APEX-Agents

Qwen3.8 27B

47.5%#5/16 open

Lab-reportedEpoch AI · Aug 2026

Inkling

33.8%#12/16 open

Lab-reportedEpoch AI · Jul 2026

CritPt

Qwen3.8 27B

5.4%#15/66 open

Lab-reportedEpoch AI · Aug 2026

Inkling

5.4%#16/66 open

Lab-reportedEpoch AI · Jul 2026

DTBench

Qwen3.8 27B

88.0%#9/68 open

Lab-reportedEpoch AI · Aug 2026

Inkling

87.5%#13/68 open

Lab-reportedEpoch AI · Jul 2026

LiveBench 2026 Coding

Qwen3.8 27B

86.8#1/15 open

IndependentLiveBench · Sep 2026

Inkling

64.0#9/15 open

IndependentLiveBench · Sep 2026

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

LiveBench 2026 Long-Horizon

Qwen3.8 27B

27.9#7/15 open

IndependentLiveBench · Sep 2026

Inkling

14.1#11/15 open

IndependentLiveBench · Sep 2026

LiveBench 2026 Reasoning

Qwen3.8 27B

80.0#6/15 open

IndependentLiveBench · Sep 2026

Inkling

78.3#9/15 open

IndependentLiveBench · Sep 2026

LMCA

Qwen3.8 27B

41.4%#7/54 open

Lab-reportedEpoch AI · Aug 2026

Inkling

37.6%#11/54 open

Lab-reportedEpoch AI · Jul 2026

ProofBench

Qwen3.8 27B

16.0%#16/26 open

Lab-reportedEpoch AI · Aug 2026

Inkling

0.0%#26/26 open

Lab-reportedEpoch AI · Jul 2026

LMArena Text

Qwen3.8 27B

1437.8#22/187 open

ArenaLMArena · Oct 2026

Inkling

1440.9#20/187 open

ArenaLMArena · Oct 2026

LMArena WebDev

Qwen3.8 27B

1593.2#10/52 open

ArenaLMArena · Oct 2026

Inkling

1413.7#26/52 open

ArenaLMArena · Oct 2026

LiveBench 2026 Browser

Qwen3.8 27B

32.0#6/15 open

IndependentLiveBench · Sep 2026

Inkling

16.0#8/15 open

IndependentLiveBench · Sep 2026

LiveBench 2026 Data Analysis

Qwen3.8 27B

76.6#5/15 open

IndependentLiveBench · Sep 2026

Inkling

72.8#8/15 open

IndependentLiveBench · Sep 2026

LiveBench 2026 Design

Qwen3.8 27B

75.9#7/15 open

IndependentLiveBench · Sep 2026

Inkling

58.3#14/15 open

IndependentLiveBench · Sep 2026

LiveBench 2026 Research

Qwen3.8 27B

59.4#12/15 open

IndependentLiveBench · Sep 2026

Inkling

59.9#11/15 open

IndependentLiveBench · Sep 2026

Only Qwen3.8 27B (1)

Surface Evolver Bench45.0%

Only Inkling (11)

VRAM by quantization

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

QuantQwen3.8 27BInkling

Q2_K

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

Inkling

405 GB~404.8 GB file

32K 412 GB · 128K 432 GB

Q3_K_S

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

Inkling

not listed

Q3_K_M

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

Inkling

465 GB~464.3 GB file

32K 471 GB · 128K 491 GB

Q4_0

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

Inkling

not listed

Q4_K_M

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

Inkling

572 GB~571.4 GB file

32K 578 GB · 128K 598 GB

Q5_K_M

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

Inkling

679 GB~678.6 GB file

32K 686 GB · 128K 705 GB

Q6_K

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

Inkling

786 GB~785.7 GB file

32K 793 GB · 128K 813 GB

Q8_0

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

Inkling

953 GB856.8 GB file

32K 959 GB · 128K 979 GB

17 more quants

IQ2_XXS

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

Inkling

not listed

IQ2_XS

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

Inkling

not listed

IQ2_S

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

Inkling

not listed

IQ2_M

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

Inkling

not listed

IQ3_XXS

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

Inkling

not listed

IQ3_XS

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

Inkling

not listed

IQ3_S

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

Inkling

not listed

IQ3_M

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

Inkling

not listed

Q3_K_L

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

Inkling

not listed

IQ4_XS

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

Inkling

not listed

IQ4_NL

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

Inkling

not listed

Q4_1

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

Inkling

not listed

Q4_K_S

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

Inkling

not listed

Q4_K_L

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

Inkling

not listed

Q5_K_S

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

Inkling

not listed

Q5_K_L

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

Inkling

not listed

BF16

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

Inkling

1905 GB1894.3 GB file

32K 1912 GB · 128K 1932 GB

How to run each

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 →

Inkling

Ollama · Q4_K_M

$ollama run hf.co/unsloth/inkling-GGUF

All ways to run Inkling →

Specifications

Specifications of Qwen3.8 27B and Inkling
Spec	Qwen3.8 27B	Inkling
Publisher	Alibaba	Thinking Machines
Parameters	27.8B	952.4B
Active parameters	—	18B per token
Architecture	Qwen3_5ForConditionalGeneration	InklingForConditionalGeneration
Context	256K tokens	—
Modalities	Vision, Function-calling	Vision, Chat, Function-calling
License	Apache 2.0	Apache 2.0
Released	Aug 2026	Jul 2026

Frequently Asked Questions

Which is better, Qwen3.8 27B or Inkling?

Qwen3.8 27B leads llmrun Score 122.1 to 116.0; only Qwen3.8 27B fits 24 GB (Q4_K_M); Inkling needs 408.4 GB even at its smallest quant. Choose Qwen3.8 27B for higher llmrun Score and stronger at agents; choose Inkling for also does chat.

Which needs less VRAM, Qwen3.8 27B or Inkling?

At Q4_K_M, Qwen3.8 27B requires 17.4 GB while Inkling needs 572.1 GB, making Qwen3.8 27B the easier model to run on your local setup.

Can I run Qwen3.8 27B or Inkling on a 16 GB GPU?

Qwen3.8 27B fits at Q3_K_L; Inkling does not fit (smallest quant needs 408.4 GB).