llmrun

Qwen3 235B A22B vs Qwen3.8 27B

Qwen3.8 27B leads llmrun Score 121.5 to 99.6; only Qwen3.8 27B fits 24 GB (Q4_K_M); Qwen3 235B A22B needs 101.8 GB even at its smallest quant.

Model A · Alibaba

Qwen3 235B A22B
99.6llmrun Score

235.1B · 22.2B active · 40K context · Apache 2.0 · Apr 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 Qwen3 235B A22B 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 99.6

  • Stronger at reasoning

    124.1 vs 99.2

  • Stronger at coding

    112.1 vs 101.3

  • Ahead on the benchmarks

    3 of 3 shared boards

  • Fits a 12 GB GPU

    IQ3_XXS · 12 GB; Qwen3 235B A22B needs 101.8 GB at its smallest quant

  • Fits a Mac 32 GB

    Q4_K_M · 17.9 GB; Qwen3 235B A22B needs 101.8 GB at its smallest quant

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

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Qwen3.8 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16Kfits

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Qwen3.8 27B

Q3_K_L · ~19 tok/s

15.4 GB · up to 16Kfits

24 GBreference

RTX 4090 · 24 GB tier

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Qwen3.8 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64Kfits

32 GB

RTX 5090 · 32 GB tier

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Qwen3.8 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256Kfits

48 GB

RTX A6000 · 48 GB tier

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kfits

Mac 32 GB

Mac Mini M4 · Macs

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Qwen3.8 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128Kfits

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfits

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3 235B A22B

Q3_K_L · ~21 tok/s

122.4 GB · up to 32K

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kmore headroom

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

Qwen3 235B A22B

99.696–103

Qwen3.8 27B

121.5119–124

Coding

Qwen3 235B A22B

101.396–107

Qwen3.8 27B

112.1105–119

Math

Qwen3 235B A22B

no data

Qwen3.8 27B

117.5111–125

Science

Qwen3 235B A22B

no data

Qwen3.8 27B

112.093–131

Reasoning

Qwen3 235B A22B

99.292–106

Qwen3.8 27B

124.1121–127

Qwen3 235B A22B · #48 of 92 open models · #30 of 71 that fit ≤192 GB

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

Benchmarks

3 shared boards: Qwen3 235B A22B leads 0, Qwen3.8 27B leads 3 · Benchmarks imported Oct 2026

LMArena Text

Qwen3 235B A22B

1402.2#46/186 open

ArenaLMArena · Oct 2026

Qwen3.8 27B

1438.1#22/186 open

ArenaLMArena · Oct 2026

DTBench

Qwen3 235B A22B

75.7%#28/68 open

Lab-reportedEpoch AI · Apr 2025

Qwen3.8 27B

88.0%#9/68 open

Lab-reportedEpoch AI · Aug 2026

LMCA

Qwen3 235B A22B

25.0%#27/54 open

Lab-reportedEpoch AI · Apr 2025

Qwen3.8 27B

41.4%#7/54 open

Lab-reportedEpoch AI · Aug 2026

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

Only Qwen3 235B A22B (8)

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

Qwen3 235B A22B

100 GB85.7 GB file

32K 103 GB · 128K —

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

Q3_K_S

Qwen3 235B A22B

103 GB101.4 GB file

32K 106 GB · 128K —

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

Q3_K_M

Qwen3 235B A22B

115 GB112.4 GB file

32K 118 GB · 128K —

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

Q4_0

Qwen3 235B A22B

not listed

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

Q4_K_M

Qwen3 235B A22B

142 GB142.2 GB file

32K 145 GB · 128K —

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

Q5_K_M

Qwen3 235B A22B

168 GB166.8 GB file

32K 171 GB · 128K —

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

Q6_K

Qwen3 235B A22B

194 GB193.0 GB file

32K 197 GB · 128K —

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

Q8_0

Qwen3 235B A22B

236 GB249.9 GB file

32K 239 GB · 128K —

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

18 more quants

IQ2_XXS

Qwen3 235B A22B

not listed

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

IQ2_XS

Qwen3 235B A22B

not listed

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

IQ2_S

Qwen3 235B A22B

not listed

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

IQ2_M

Qwen3 235B A22B

not listed

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

IQ3_XXS

Qwen3 235B A22B

not listed

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

IQ3_XS

Qwen3 235B A22B

not listed

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

IQ3_S

Qwen3 235B A22B

not listed

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

IQ3_M

Qwen3 235B A22B

not listed

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

Q3_K_L

Qwen3 235B A22B

121 GB111.2 GB file

32K 124 GB · 128K —

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

IQ4_XS

Qwen3 235B A22B

127 GB125.5 GB file

32K 130 GB · 128K —

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

IQ4_NL

Qwen3 235B A22B

not listed

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_1

Qwen3 235B A22B

133 GB147.2 GB file

32K 136 GB · 128K —

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_S

Qwen3 235B A22B

133 GB133.7 GB file

32K 136 GB · 128K —

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_L

Qwen3 235B A22B

not listed

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

Q5_0

Qwen3 235B A22B

147 GB161.9 GB file

32K 150 GB · 128K —

Qwen3.8 27B

not listed

Q5_K_S

Qwen3 235B A22B

162 GB161.9 GB file

32K 165 GB · 128K —

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

Q5_K_L

Qwen3 235B A22B

not listed

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

BF16

Qwen3 235B A22B

471 GB470.3 GB file

32K 474 GB · 128K —

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

How to run each

Specifications

Specifications of Qwen3 235B A22B and Qwen3.8 27B
SpecQwen3 235B A22BQwen3.8 27B
PublisherAlibabaAlibaba
Parameters235.1B27.8B
Active parameters22B per token—
ArchitectureQwen3MoeForCausalLMQwen3_5ForConditionalGeneration
Context40K tokens256K tokens
ModalitiesChat, Function-callingVision, Function-calling
LicenseApache 2.0Apache 2.0
ReleasedApr 2025Aug 2026

Frequently Asked Questions

Which is better, Qwen3 235B A22B or Qwen3.8 27B?

Qwen3.8 27B leads llmrun Score 121.5 to 99.6; only Qwen3.8 27B fits 24 GB (Q4_K_M); Qwen3 235B A22B needs 101.8 GB even at its smallest quant. Choose Qwen3 235B A22B for also does chat; choose Qwen3.8 27B for higher llmrun Score and stronger at reasoning.

Which needs less VRAM, Qwen3 235B A22B or Qwen3.8 27B?

At Q4_K_M, Qwen3 235B A22B requires 141.6 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 Qwen3 235B A22B or Qwen3.8 27B on a 16 GB GPU?

Qwen3 235B A22B does not fit (smallest quant needs 101.8 GB); Qwen3.8 27B fits at Q3_K_L.

Which has a longer context window, Qwen3 235B A22B or Qwen3.8 27B?

Qwen3 235B A22B supports 40,960 tokens and Qwen3.8 27B supports 262,144 tokens.

Qwen3 235B A22B vs Qwen3.8 27B — VRAM & GPU Comparison | llmrun