Qwen3.5 122B A10B vs Qwen3.8 27B

Qwen3.8 27B leads llmrun Score 121.5 to 109.4; only Qwen3.8 27B fits 24 GB (Q4_K_M); Qwen3.5 122B A10B needs 34.9 GB even at its smallest quant.

Model A · Alibaba

Qwen3.5 122B A10B

109.4llmrun Score

125.1B · 12.7B active · 256K context · Apache 2.0 · Feb 2026

VisionFunctions

Model B · Alibaba

Qwen3.8 27B

121.5llmrun Score

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

VisionFunctions

Which should you choose?

Choose Qwen3.8 27B if you want…

Higher llmrun Score
121.5 vs 109.4
Stronger at science
112.0 vs 96.0
Stronger at reasoning
124.1 vs 112.4
Ahead on the benchmarks
6 of 6 shared boards
Fits a 12 GB GPU
IQ3_XXS · 12 GB; Qwen3.5 122B A10B needs 34.9 GB at its smallest quant
Fits a Mac 32 GB
Q4_K_M · 17.9 GB; Qwen3.5 122B A10B needs 34.9 GB at its smallest quant

Qwen3.5 122B A10B: 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%.

MemoryQwen3.5 122B A10BQwen3.8 27B

8 GB

RTX 4060 · 8 GB tier

Qwen3.5 122B A10B

Doesn't fit

smallest quant needs 34.9 GB

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3.5 122B A10B

Doesn't fit

smallest quant needs 34.9 GB

Qwen3.8 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16Kfits

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Qwen3.5 122B A10B

Doesn't fit

smallest quant needs 34.9 GB

Qwen3.8 27B

Q3_K_L · ~19 tok/s

15.4 GB · up to 16Kfits

24 GBreference

RTX 4090 · 24 GB tier

Qwen3.5 122B A10B

Doesn't fit

smallest quant needs 34.9 GB

Qwen3.8 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64Kfits

32 GB

RTX 5090 · 32 GB tier

Qwen3.5 122B A10B

Doesn't fit

smallest quant needs 34.9 GB

Qwen3.8 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256Kfits

48 GB

RTX A6000 · 48 GB tier

Qwen3.5 122B A10B

IQ2_M · ~88 tok/s

42.7 GB · up to 256K

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kmore headroom

Mac 32 GB

Mac Mini M4 · Macs

Qwen3.5 122B A10B

Doesn't fit

smallest quant needs 34.9 GB

Qwen3.8 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128Kfits

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen3.5 122B A10B

IQ3_M · ~41 tok/s

56.7 GB · up to 256K

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kmore headroom

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3.5 122B A10B

Q4_K_M · ~34 tok/s

75.5 GB · up to 256Kfaster

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

Qwen3.5 122B A10B Qwen3.8 27B

Overall

Qwen3.5 122B A10B

109.4102–117

Qwen3.8 27B

121.5119–124

Coding

Qwen3.5 122B A10B

no data

Qwen3.8 27B

112.1105–119

Math

Qwen3.5 122B A10B

no data

Qwen3.8 27B

117.5111–125

Science

Qwen3.5 122B A10B

96.074–118

Qwen3.8 27B

112.093–131

Reasoning

Qwen3.5 122B A10B

112.4104–120

Qwen3.8 27B

124.1121–127

Qwen3.5 122B A10B · #25 of 92 open models · #6 of 54 that fit ≤96 GB

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

Benchmarks

6 shared boards: Qwen3.5 122B A10B leads 0, Qwen3.8 27B leads 6 · Benchmarks imported Oct 2026

BoardQwen3.5 122B A10BQwen3.8 27B

LMArena Text

Qwen3.5 122B A10B

1416.3#37/186 open

ArenaLMArena · Oct 2026

Qwen3.8 27B

1438.1#22/186 open

ArenaLMArena · Oct 2026

LMArena WebDev

Qwen3.5 122B A10B

1360.4#32/50 open

ArenaLMArena · Oct 2026

Qwen3.8 27B

1592.8#10/50 open

ArenaLMArena · Oct 2026

SciCode

Qwen3.5 122B A10B

35.6%#43/65 open

Lab-reportedEpoch AI · Feb 2026

Qwen3.8 27B

46.6%#19/65 open

Lab-reportedEpoch AI · Aug 2026

CritPt

Qwen3.5 122B A10B

0.9%#35/65 open

Lab-reportedEpoch AI · Feb 2026

Qwen3.8 27B

5.4%#15/65 open

Lab-reportedEpoch AI · Aug 2026

DTBench

Qwen3.5 122B A10B

84.3%#17/68 open

Lab-reportedEpoch AI · Feb 2026

Qwen3.8 27B

88.0%#9/68 open

Lab-reportedEpoch AI · Aug 2026

LMCA

Qwen3.5 122B A10B

32.2%#18/54 open

Lab-reportedEpoch AI · Feb 2026

Qwen3.8 27B

41.4%#7/54 open

Lab-reportedEpoch AI · Aug 2026

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

Only Qwen3.5 122B A10B (2)

MMLU-Pro86.7%
Mystery Game Puzzles17.0%

Only Qwen3.8 27B (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.

QuantQwen3.5 122B A10BQwen3.8 27B

Q2_K

Qwen3.5 122B A10B

53.5 GB46.4 GB file

32K 53.8 GB · 128K 54.7 GB

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

Q3_K_S

Qwen3.5 122B A10B

55.1 GB52.5 GB file

32K 55.3 GB · 128K 56.2 GB

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

Q3_K_M

Qwen3.5 122B A10B

61.4 GB56.4 GB file

32K 61.6 GB · 128K 62.5 GB

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

Q4_0

Qwen3.5 122B A10B

62.9 GB72.5 GB file

32K 63.2 GB · 128K 64.1 GB

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

Q4_K_M

Qwen3.5 122B A10B

75.4 GB76.5 GB file

32K 75.7 GB · 128K 76.6 GB

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

Q5_K_M

Qwen3.5 122B A10B

89.5 GB91.5 GB file

32K 89.7 GB · 128K 90.6 GB

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

Q6_K

Qwen3.5 122B A10B

104 GB101.0 GB file

32K 104 GB · 128K 105 GB

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

Q8_0

Qwen3.5 122B A10B

125 GB129.9 GB file

32K 126 GB · 128K 127 GB

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

18 more quants

IQ2_XXS

Qwen3.5 122B A10B

34.8 GB36.6 GB file

32K 35.0 GB · 128K 35.9 GB

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

IQ2_XS

Qwen3.5 122B A10B

37.9 GB40.0 GB file

32K 38.1 GB · 128K 39.0 GB

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

IQ2_S

Qwen3.5 122B A10B

39.5 GB40.6 GB file

32K 39.7 GB · 128K 40.6 GB

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

IQ2_M

Qwen3.5 122B A10B

42.6 GB39.1 GB file

32K 42.8 GB · 128K 43.7 GB

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

IQ3_XXS

Qwen3.5 122B A10B

48.9 GB44.7 GB file

32K 49.1 GB · 128K 50.0 GB

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

Q2_K_S

Qwen3.5 122B A10B

50.4 GB41.7 GB file

32K 50.6 GB · 128K 51.5 GB

Qwen3.8 27B

not listed

IQ3_XS

Qwen3.5 122B A10B

52.0 GB59.2 GB file

32K 52.2 GB · 128K 53.1 GB

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

IQ3_S

Qwen3.5 122B A10B

53.5 GB46.6 GB file

32K 53.8 GB · 128K 54.7 GB

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

IQ3_M

Qwen3.5 122B A10B

56.7 GB61.6 GB file

32K 56.9 GB · 128K 57.8 GB

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

Q3_K_L

Qwen3.5 122B A10B

64.5 GB61.6 GB file

32K 64.7 GB · 128K 65.6 GB

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

IQ4_XS

Qwen3.5 122B A10B

67.6 GB60.2 GB file

32K 67.8 GB · 128K 68.7 GB

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

IQ4_NL

Qwen3.5 122B A10B

70.7 GB61.4 GB file

32K 71.0 GB · 128K 71.9 GB

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_1

Qwen3.5 122B A10B

70.7 GB79.7 GB file

32K 71.0 GB · 128K 71.9 GB

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_S

Qwen3.5 122B A10B

70.7 GB71.7 GB file

32K 71.0 GB · 128K 71.9 GB

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_L

Qwen3.5 122B A10B

77.0 GB78.2 GB file

32K 77.2 GB · 128K 78.1 GB

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

Q5_K_S

Qwen3.5 122B A10B

86.4 GB86.4 GB file

32K 86.6 GB · 128K 87.5 GB

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

Q5_K_L

Qwen3.5 122B A10B

91.1 GB90.9 GB file

32K 91.3 GB · 128K 92.2 GB

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

BF16

Qwen3.5 122B A10B

251 GB244.3 GB file

32K 251 GB · 128K 252 GB

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

How to run each

Qwen3.5 122B A10B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3.5-122B-A10B-GGUF:Q4_K_M

All ways to run Qwen3.5 122B A10B →

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 Qwen3.5 122B A10B and Qwen3.8 27B
Spec	Qwen3.5 122B A10B	Qwen3.8 27B
Publisher	Alibaba	Alibaba
Parameters	125.1B	27.8B
Active parameters	13B per token	—
Architecture	Qwen3_5MoeForConditionalGeneration	Qwen3_5ForConditionalGeneration
Context	256K tokens	256K tokens
Modalities	Vision, Function-calling	Vision, Function-calling
License	Apache 2.0	Apache 2.0
Released	Feb 2026	Aug 2026

Frequently Asked Questions

Which is better, Qwen3.5 122B A10B or Qwen3.8 27B?

Qwen3.8 27B leads llmrun Score 121.5 to 109.4; only Qwen3.8 27B fits 24 GB (Q4_K_M); Qwen3.5 122B A10B needs 34.9 GB even at its smallest quant. Choose Qwen3.8 27B for higher llmrun Score and stronger at science.

Which needs less VRAM, Qwen3.5 122B A10B or Qwen3.8 27B?

At Q4_K_M, Qwen3.5 122B A10B requires 75.4 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 Qwen3.5 122B A10B or Qwen3.8 27B on a 16 GB GPU?

Qwen3.5 122B A10B does not fit (smallest quant needs 34.9 GB); Qwen3.8 27B fits at Q3_K_L.

Which has a longer context window, Qwen3.5 122B A10B or Qwen3.8 27B?

Qwen3.5 122B A10B supports 262,144 tokens and Qwen3.8 27B supports 262,144 tokens.