Qwen3.5 397B A17B vs Qwen3.8 27B

Qwen3.8 27B leads llmrun Score 121.5 to 112.6; only Qwen3.8 27B fits 24 GB (Q4_K_M); Qwen3.5 397B A17B needs 111.5 GB even at its smallest quant.

Model A · Alibaba

Qwen3.5 397B A17B

112.6llmrun Score

403.4B · 24.4B 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 112.6
Stronger at reasoning
124.1 vs 114.6
Ahead on the benchmarks
3 of 4 shared boards
Fits a 12 GB GPU
IQ3_XXS · 12 GB; Qwen3.5 397B A17B needs 111.5 GB at its smallest quant
Fits a Mac 32 GB
Q4_K_M · 17.9 GB; Qwen3.5 397B A17B needs 111.5 GB at its smallest quant
Lighter on memory
17.4 vs 242.5 GB at Q4_K_M

Qwen3.5 397B A17B: 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 397B A17BQwen3.8 27B

8 GB

RTX 4060 · 8 GB tier

Qwen3.5 397B A17B

Doesn't fit

smallest quant needs 111.5 GB

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3.5 397B A17B

Doesn't fit

smallest quant needs 111.5 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 397B A17B

Doesn't fit

smallest quant needs 111.5 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 397B A17B

Doesn't fit

smallest quant needs 111.5 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 397B A17B

Doesn't fit

smallest quant needs 111.5 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 397B A17B

Doesn't fit

smallest quant needs 111.5 GB

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kfits

Mac 32 GB

Mac Mini M4 · Macs

Qwen3.5 397B A17B

Doesn't fit

smallest quant needs 111.5 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 397B A17B

Doesn't fit

smallest quant needs 111.5 GB

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfits

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3.5 397B A17B

IQ2_XS · ~32 tok/s

121.6 GB · up to 128K

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

Qwen3.5 397B A17B Qwen3.8 27B

Overall

Qwen3.5 397B A17B

112.6109–117

Qwen3.8 27B

121.5119–124

Coding

Qwen3.5 397B A17B

no data

Qwen3.8 27B

112.1105–119

Math

Qwen3.5 397B A17B

112.4107–118

Qwen3.8 27B

117.5111–125

Science

Qwen3.5 397B A17B

no data

Qwen3.8 27B

112.093–131

Reasoning

Qwen3.5 397B A17B

114.6107–122

Qwen3.8 27B

124.1121–127

Qwen3.5 397B A17B · #18 of 92 open models · #8 of 77 that fit ≤256 GB

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

Benchmarks

4 shared boards: Qwen3.5 397B A17B leads 0, Qwen3.8 27B leads 3 · Benchmarks imported Oct 2026

BoardQwen3.5 397B A17BQwen3.8 27B

LMArena Text

Qwen3.5 397B A17B

1441.7#17/186 open

ArenaLMArena · Oct 2026

Qwen3.8 27B

1438.1#22/186 open

ArenaLMArena · Oct 2026

LMArena WebDev

Qwen3.5 397B A17B

1399.9#26/50 open

ArenaLMArena · Oct 2026

Qwen3.8 27B

1592.8#10/50 open

ArenaLMArena · Oct 2026

DTBench

Qwen3.5 397B A17B

87.5%#12/68 open

Lab-reportedEpoch AI · Feb 2026

Qwen3.8 27B

88.0%#9/68 open

Lab-reportedEpoch AI · Aug 2026

LMCA

Qwen3.5 397B A17B

37.9%#10/54 open

Lab-reportedEpoch AI · Feb 2026

Qwen3.8 27B

41.4%#7/54 open

Lab-reportedEpoch AI · Aug 2026

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

APEX-Agents

Qwen3.5 397B A17B

24.9%#13/16 open

Lab-reportedEpoch AI · Feb 2026

Qwen3.8 27B

47.5%#5/16 open

Lab-reportedEpoch AI · Aug 2026

Only Qwen3.5 397B A17B (6)

Only Qwen3.8 27B (9)

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 397B A17BQwen3.8 27B

Q2_K

Qwen3.5 397B A17B

172 GB146.3 GB file

32K 172 GB · 128K 174 GB

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

Q3_K_S

Qwen3.5 397B A17B

177 GB164.3 GB file

32K 177 GB · 128K 179 GB

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

Q3_K_M

Qwen3.5 397B A17B

197 GB177.4 GB file

32K 197 GB · 128K 199 GB

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

Q4_0

Qwen3.5 397B A17B

202 GB~201.7 GB file

32K 203 GB · 128K 204 GB

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

Q4_K_M

Qwen3.5 397B A17B

242 GB244.1 GB file

32K 243 GB · 128K 244 GB

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

Q5_K_M

Qwen3.5 397B A17B

288 GB293.7 GB file

32K 288 GB · 128K 290 GB

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

Q6_K

Qwen3.5 397B A17B

333 GB326.6 GB file

32K 334 GB · 128K 335 GB

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

Q8_0

Qwen3.5 397B A17B

404 GB421.5 GB file

32K 404 GB · 128K 406 GB

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

17 more quants

IQ2_XXS

Qwen3.5 397B A17B

111 GB114.9 GB file

32K 112 GB · 128K 113 GB

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

IQ2_XS

Qwen3.5 397B A17B

121 GB125.4 GB file

32K 122 GB · 128K 123 GB

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

IQ2_S

Qwen3.5 397B A17B

126 GB127.3 GB file

32K 127 GB · 128K 128 GB

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

IQ2_M

Qwen3.5 397B A17B

137 GB123.1 GB file

32K 137 GB · 128K 138 GB

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

IQ3_XXS

Qwen3.5 397B A17B

157 GB140.3 GB file

32K 157 GB · 128K 159 GB

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

IQ3_XS

Qwen3.5 397B A17B

167 GB188.2 GB file

32K 167 GB · 128K 169 GB

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

IQ3_S

Qwen3.5 397B A17B

172 GB146.4 GB file

32K 172 GB · 128K 174 GB

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

IQ3_M

Qwen3.5 397B A17B

182 GB196.0 GB file

32K 182 GB · 128K 184 GB

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

Q3_K_L

Qwen3.5 397B A17B

207 GB195.9 GB file

32K 208 GB · 128K 209 GB

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

IQ4_XS

Qwen3.5 397B A17B

217 GB189.7 GB file

32K 218 GB · 128K 219 GB

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

IQ4_NL

Qwen3.5 397B A17B

227 GB193.8 GB file

32K 228 GB · 128K 229 GB

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_1

Qwen3.5 397B A17B

227 GB256.1 GB file

32K 228 GB · 128K 229 GB

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_S

Qwen3.5 397B A17B

227 GB228.0 GB file

32K 228 GB · 128K 229 GB

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_L

Qwen3.5 397B A17B

248 GB249.0 GB file

32K 248 GB · 128K 249 GB

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

Q5_K_S

Qwen3.5 397B A17B

278 GB276.6 GB file

32K 278 GB · 128K 280 GB

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

Q5_K_L

Qwen3.5 397B A17B

293 GB290.6 GB file

32K 293 GB · 128K 295 GB

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

BF16

Qwen3.5 397B A17B

807 GB793.0 GB file

32K 808 GB · 128K 809 GB

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

How to run each

Qwen3.5 397B A17B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3.5-397B-A17B-GGUF:Q4_K_M

All ways to run Qwen3.5 397B A17B →

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 397B A17B and Qwen3.8 27B
Spec	Qwen3.5 397B A17B	Qwen3.8 27B
Publisher	Alibaba	Alibaba
Parameters	403.4B	27.8B
Active parameters	24B 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 397B A17B or Qwen3.8 27B?

Qwen3.8 27B leads llmrun Score 121.5 to 112.6; only Qwen3.8 27B fits 24 GB (Q4_K_M); Qwen3.5 397B A17B needs 111.5 GB even at its smallest quant. Choose Qwen3.8 27B for higher llmrun Score and stronger at reasoning.

Which needs less VRAM, Qwen3.5 397B A17B or Qwen3.8 27B?

At Q4_K_M, Qwen3.5 397B A17B requires 242.5 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 397B A17B or Qwen3.8 27B on a 16 GB GPU?

Qwen3.5 397B A17B does not fit (smallest quant needs 111.5 GB); Qwen3.8 27B fits at Q3_K_L.

Which has a longer context window, Qwen3.5 397B A17B or Qwen3.8 27B?

Qwen3.5 397B A17B supports 262,144 tokens and Qwen3.8 27B supports 262,144 tokens.