Qwen3.6 27B vs Qwen3.8 27B

Qwen3.8 27B leads llmrun Score 121.5 to 111.4; both fit 24 GB at Q4_K_M.

Model A · Alibaba

111.4llmrun Score

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

VisionFunctions

Model B · Alibaba

121.5llmrun Score

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

VisionFunctions

Which should you choose?

Choose Qwen3.8 27B if you want…

Higher llmrun Score
121.5 vs 111.4
Stronger at reasoning
124.1 vs 106.4
Stronger at coding
112.1 vs 102.3
Ahead on the benchmarks
7 of 7 shared boards
Newer release
Aug 2026 vs Apr 2026

Qwen3.6 27B: no clear edge over Qwen3.8 27B in the data we have.

On your hardware

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

MemoryQwen3.6 27BQwen3.8 27B

8 GB

RTX 4060 · 8 GB tier

Qwen3.6 27B

Doesn't fit

smallest quant needs 8.8 GB

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3.6 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16K

Qwen3.8 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16K

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Qwen3.6 27B

Q3_K_L · ~19 tok/s

15.4 GB · up to 16K

Qwen3.8 27B

Q3_K_L · ~19 tok/s

15.4 GB · up to 16K

24 GBreference

RTX 4090 · 24 GB tier

Qwen3.6 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64K

Qwen3.8 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64K

32 GB

RTX 5090 · 32 GB tier

Qwen3.6 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256K

Qwen3.8 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256K

48 GB

RTX A6000 · 48 GB tier

Qwen3.6 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256K

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256K

Mac 32 GB

Mac Mini M4 · Macs

Qwen3.6 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128K

Qwen3.8 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128K

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen3.6 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256K

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256K

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3.6 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256K

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256K

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

Qwen3.6 27B Qwen3.8 27B

Overall

Qwen3.6 27B

111.4108–115

Qwen3.8 27B

121.5119–124

Coding

Qwen3.6 27B

102.384–121

Qwen3.8 27B

112.1105–119

Math

Qwen3.6 27B

113.7108–119

Qwen3.8 27B

117.5111–125

Science

Qwen3.6 27B

111.1102–120

Qwen3.8 27B

112.093–131

Reasoning

Qwen3.6 27B

106.499–114

Qwen3.8 27B

124.1121–127

Qwen3.6 27B · #20 of 92 open models · #2 of 34 that fit 24 GB

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

Benchmarks

7 shared boards: Qwen3.6 27B leads 0, Qwen3.8 27B leads 7 · Benchmarks imported Oct 2026

BoardQwen3.6 27BQwen3.8 27B

LiveBench Coding

Qwen3.6 27B

71.8#13/19 open

IndependentLiveBench · Jun 2026

Qwen3.8 27B

75.7#9/19 open

IndependentLiveBench · Jun 2026

LiveBench Reasoning

Qwen3.6 27B

70.3#19/19 open

IndependentLiveBench · Jun 2026

Qwen3.8 27B

80.0#11/19 open

IndependentLiveBench · Jun 2026

Qwen3.6 27B

79.9#16/19 open

IndependentLiveBench · Jun 2026

Qwen3.8 27B

86.2#11/19 open

IndependentLiveBench · Jun 2026

Qwen3.6 27B

37.3%#35/65 open

Lab-reportedEpoch AI · Apr 2026

Qwen3.8 27B

46.6%#19/65 open

Lab-reportedEpoch AI · Aug 2026

Qwen3.6 27B

0.9%#36/65 open

Lab-reportedEpoch AI · Apr 2026

Qwen3.8 27B

5.4%#15/65 open

Lab-reportedEpoch AI · Aug 2026

Qwen3.6 27B

78.1%#26/68 open

Lab-reportedEpoch AI · Apr 2026

Qwen3.8 27B

88.0%#9/68 open

Lab-reportedEpoch AI · Aug 2026

Qwen3.6 27B

34.5%#15/54 open

Lab-reportedEpoch AI · Apr 2026

Qwen3.8 27B

41.4%#7/54 open

Lab-reportedEpoch AI · Aug 2026

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

Only Qwen3.6 27B (5)

Only Qwen3.8 27B (7)

VRAM by quantization

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

QuantQwen3.6 27BQwen3.8 27B

Q2_K

Qwen3.6 27B

12.6 GB12.1 GB file

32K 13.9 GB · 128K 19.3 GB

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

Q3_K_S

Qwen3.6 27B

12.9 GB12.4 GB file

32K 14.2 GB · 128K 19.6 GB

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

Q3_K_M

Qwen3.6 27B

14.3 GB13.6 GB file

32K 15.6 GB · 128K 21.0 GB

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

Q4_0

Qwen3.6 27B

14.6 GB15.8 GB file

32K 16.0 GB · 128K 21.4 GB

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

Q4_K_M

Qwen3.6 27B

17.4 GB16.8 GB file

32K 18.8 GB · 128K 24.1 GB

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

Q5_K_M

Qwen3.6 27B

20.5 GB19.5 GB file

32K 21.9 GB · 128K 27.3 GB

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

Q6_K

Qwen3.6 27B

23.7 GB22.5 GB file

32K 25.0 GB · 128K 30.4 GB

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

Q8_0

Qwen3.6 27B

28.5 GB28.6 GB file

32K 29.9 GB · 128K 35.2 GB

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

17 more quants

IQ2_XXS

Qwen3.6 27B

8.4 GB9.4 GB file

32K 9.7 GB · 128K 15.1 GB

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

IQ2_XS

Qwen3.6 27B

9.1 GB10.2 GB file

32K 10.4 GB · 128K 15.8 GB

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

IQ2_S

Qwen3.6 27B

9.4 GB10.5 GB file

32K 10.8 GB · 128K 16.1 GB

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

IQ2_M

Qwen3.6 27B

10.1 GB10.8 GB file

32K 11.5 GB · 128K 16.8 GB

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

IQ3_XXS

Qwen3.6 27B

11.5 GB12.0 GB file

32K 12.9 GB · 128K 18.2 GB

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

IQ3_XS

Qwen3.6 27B

12.2 GB13.5 GB file

32K 13.6 GB · 128K 18.9 GB

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

IQ3_S

Qwen3.6 27B

not listed

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

IQ3_M

Qwen3.6 27B

13.3 GB14.1 GB file

32K 14.6 GB · 128K 20.0 GB

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

Q3_K_L

Qwen3.6 27B

15.0 GB15.5 GB file

32K 16.3 GB · 128K 21.7 GB

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

IQ4_XS

Qwen3.6 27B

15.7 GB15.4 GB file

32K 17.0 GB · 128K 22.4 GB

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

IQ4_NL

Qwen3.6 27B

16.4 GB16.1 GB file

32K 17.7 GB · 128K 23.1 GB

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_1

Qwen3.6 27B

16.4 GB17.3 GB file

32K 17.7 GB · 128K 23.1 GB

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_S

Qwen3.6 27B

16.4 GB15.9 GB file

32K 17.7 GB · 128K 23.1 GB

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_L

Qwen3.6 27B

17.8 GB18.9 GB file

32K 19.1 GB · 128K 24.5 GB

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

Q5_K_S

Qwen3.6 27B

19.9 GB19.0 GB file

32K 21.2 GB · 128K 26.6 GB

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

Q5_K_L

Qwen3.6 27B

20.9 GB21.7 GB file

32K 22.2 GB · 128K 27.6 GB

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

BF16

Qwen3.6 27B

56.3 GB53.8 GB file

32K 57.7 GB · 128K 63.0 GB

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

How to run each

Qwen3.6 27B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3.6-27B-GGUF:Q4_K_M

All ways to run Qwen3.6 27B →

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 Qwen3.6 27B and Qwen3.8 27B
Spec	Qwen3.6 27B	Qwen3.8 27B
Publisher	Alibaba	Alibaba
Parameters	27.8B	27.8B
Architecture	Qwen3_5ForConditionalGeneration	Qwen3_5ForConditionalGeneration
Context	256K tokens	256K tokens
Modalities	Vision, Function-calling	Vision, Function-calling
License	Apache 2.0	Apache 2.0
Released	Apr 2026	Aug 2026

Frequently Asked Questions

Which is better, Qwen3.6 27B or Qwen3.8 27B?

Qwen3.8 27B leads llmrun Score 121.5 to 111.4; both fit 24 GB at Q4_K_M. Choose Qwen3.8 27B for higher llmrun Score and stronger at reasoning.

Which needs less VRAM, Qwen3.6 27B or Qwen3.8 27B?

At Q4_K_M, Qwen3.6 27B requires 17.4 GB while Qwen3.8 27B needs 17.4 GB, making Qwen3.6 27B the easier model to run on your local setup.

Which is faster on RTX 4090?

Estimated decode speed on RTX 4090 is about 38 tok/s for Qwen3.6 27B (Q4_K_M) and 38 tok/s for Qwen3.8 27B (Q4_K_M), so Qwen3.6 27B is faster. Estimates, ±20%.

Can I run Qwen3.6 27B or Qwen3.8 27B on a 16 GB GPU?

Qwen3.6 27B fits at Q3_K_L; Qwen3.8 27B fits at Q3_K_L.

Which has a longer context window, Qwen3.6 27B or Qwen3.8 27B?

Qwen3.6 27B supports 262,144 tokens and Qwen3.8 27B supports 262,144 tokens.

Qwen3.6 27B vs Qwen3.8 27B — VRAM & GPU Comparison | llmrun