DeepSeek V3.1 Terminus vs Qwen3.8 27B

Qwen3.8 27B leads llmrun Score 121.5 to 107.7; only Qwen3.8 27B fits 24 GB (Q4_K_M); DeepSeek V3.1 Terminus needs 189.7 GB even at its smallest quant.

Model A · DeepSeek

DeepSeek V3.1 Terminus

107.7llmrun Score

684.5B · 40.1B active · 160K context · MIT · Sep 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 DeepSeek V3.1 Terminus 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 107.7
Stronger at reasoning
124.1 vs 107.6
Stronger at science
112.0 vs 102.8
Ahead on the benchmarks
5 of 5 shared boards
Fits a 12 GB GPU
IQ3_XXS · 12 GB; DeepSeek V3.1 Terminus needs 189.7 GB at its smallest quant
Fits a Mac 32 GB
Q4_K_M · 17.9 GB; DeepSeek V3.1 Terminus needs 189.7 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%.

MemoryDeepSeek V3.1 TerminusQwen3.8 27B

8 GB

RTX 4060 · 8 GB tier

DeepSeek V3.1 Terminus

Doesn't fit

smallest quant needs 189.7 GB

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

DeepSeek V3.1 Terminus

Doesn't fit

smallest quant needs 189.7 GB

Qwen3.8 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16Kfits

16 GB

RTX 5060 Ti 16GB · 16 GB tier

DeepSeek V3.1 Terminus

Doesn't fit

smallest quant needs 189.7 GB

Qwen3.8 27B

Q3_K_L · ~19 tok/s

15.4 GB · up to 16Kfits

24 GBreference

RTX 4090 · 24 GB tier

DeepSeek V3.1 Terminus

Doesn't fit

smallest quant needs 189.7 GB

Qwen3.8 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64Kfits

32 GB

RTX 5090 · 32 GB tier

DeepSeek V3.1 Terminus

Doesn't fit

smallest quant needs 189.7 GB

Qwen3.8 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256Kfits

48 GB

RTX A6000 · 48 GB tier

DeepSeek V3.1 Terminus

Doesn't fit

smallest quant needs 189.7 GB

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kfits

Mac 32 GB

Mac Mini M4 · Macs

DeepSeek V3.1 Terminus

Doesn't fit

smallest quant needs 189.7 GB

Qwen3.8 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128Kfits

Mac 64 GB

Mac Studio M4 Max · Macs

DeepSeek V3.1 Terminus

Doesn't fit

smallest quant needs 189.7 GB

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfits

Mac 128 GB

Mac Studio M4 Max · Macs

DeepSeek V3.1 Terminus

Doesn't fit

smallest quant needs 189.7 GB

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfits

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

DeepSeek V3.1 Terminus Qwen3.8 27B

Overall

DeepSeek V3.1 Terminus

107.7101–115

Qwen3.8 27B

121.5119–124

Coding

DeepSeek V3.1 Terminus

108.397–120

Qwen3.8 27B

112.1105–119

Math

DeepSeek V3.1 Terminus

no data

Qwen3.8 27B

117.5111–125

Science

DeepSeek V3.1 Terminus

102.882–124

Qwen3.8 27B

112.093–131

Reasoning

DeepSeek V3.1 Terminus

107.699–116

Qwen3.8 27B

124.1121–127

DeepSeek V3.1 Terminus · #32 of 92 open models · #29 of 88 that fit ≤512 GB

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

Benchmarks

5 shared boards: DeepSeek V3.1 Terminus leads 0, Qwen3.8 27B leads 5 · Benchmarks imported Oct 2026

BoardDeepSeek V3.1 TerminusQwen3.8 27B

LMArena Text

DeepSeek V3.1 Terminus

1416.0#38/186 open

ArenaLMArena · Oct 2026

Qwen3.8 27B

1438.1#22/186 open

ArenaLMArena · Oct 2026

SciCode

DeepSeek V3.1 Terminus

40.6%#28/65 open

Lab-reportedEpoch AI · Sep 2025

Qwen3.8 27B

46.6%#19/65 open

Lab-reportedEpoch AI · Aug 2026

CritPt

DeepSeek V3.1 Terminus

1.7%#27/65 open

Lab-reportedEpoch AI · Sep 2025

Qwen3.8 27B

5.4%#15/65 open

Lab-reportedEpoch AI · Aug 2026

DTBench

DeepSeek V3.1 Terminus

81.3%#21/68 open

Lab-reportedEpoch AI · Sep 2025

Qwen3.8 27B

88.0%#9/68 open

Lab-reportedEpoch AI · Aug 2026

LMCA

DeepSeek V3.1 Terminus

28.6%#26/54 open

Lab-reportedEpoch AI · Sep 2025

Qwen3.8 27B

41.4%#7/54 open

Lab-reportedEpoch AI · Aug 2026

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

Only DeepSeek V3.1 Terminus (1)

ALE-Bench745.2

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.

QuantDeepSeek V3.1 TerminusQwen3.8 27B

Q2_K

DeepSeek V3.1 Terminus

295 GB245.7 GB file

32K 294 GB · 128K 300 GB

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

Q3_K_S

DeepSeek V3.1 Terminus

303 GB290.4 GB file

32K 302 GB · 128K 309 GB

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

Q3_K_M

DeepSeek V3.1 Terminus

338 GB320.5 GB file

32K 336 GB · 128K 343 GB

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

Q4_0

DeepSeek V3.1 Terminus

346 GB380.1 GB file

32K 345 GB · 128K 352 GB

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

Q4_K_M

DeepSeek V3.1 Terminus

415 GB405.4 GB file

32K 413 GB · 128K 420 GB

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

Q5_K_M

DeepSeek V3.1 Terminus

492 GB476.2 GB file

32K 490 GB · 128K 497 GB

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

Q6_K

DeepSeek V3.1 Terminus

569 GB551.3 GB file

32K 567 GB · 128K 574 GB

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

Q8_0

DeepSeek V3.1 Terminus

688 GB713.3 GB file

32K 687 GB · 128K 694 GB

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

17 more quants

IQ2_XXS

DeepSeek V3.1 Terminus

192 GB217.1 GB file

32K 191 GB · 128K 198 GB

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

IQ2_XS

DeepSeek V3.1 Terminus

209 GB188.4 GB file

32K 208 GB · 128K 215 GB

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

IQ2_S

DeepSeek V3.1 Terminus

218 GB189.6 GB file

32K 217 GB · 128K 223 GB

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

IQ2_M

DeepSeek V3.1 Terminus

235 GB228.9 GB file

32K 234 GB · 128K 241 GB

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

IQ3_XXS

DeepSeek V3.1 Terminus

269 GB273.5 GB file

32K 268 GB · 128K 275 GB

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

IQ3_XS

DeepSeek V3.1 Terminus

286 GB277.1 GB file

32K 285 GB · 128K 292 GB

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

IQ3_S

DeepSeek V3.1 Terminus

not listed

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

IQ3_M

DeepSeek V3.1 Terminus

312 GB307.9 GB file

32K 311 GB · 128K 318 GB

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

Q3_K_L

DeepSeek V3.1 Terminus

355 GB319.7 GB file

32K 353 GB · 128K 360 GB

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

IQ4_XS

DeepSeek V3.1 Terminus

372 GB358.3 GB file

32K 371 GB · 128K 377 GB

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

IQ4_NL

DeepSeek V3.1 Terminus

389 GB379.1 GB file

32K 388 GB · 128K 395 GB

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_1

DeepSeek V3.1 Terminus

389 GB420.8 GB file

32K 388 GB · 128K 395 GB

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_S

DeepSeek V3.1 Terminus

389 GB381.1 GB file

32K 388 GB · 128K 395 GB

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_L

DeepSeek V3.1 Terminus

not listed

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

Q5_K_S

DeepSeek V3.1 Terminus

475 GB462.6 GB file

32K 473 GB · 128K 480 GB

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

Q5_K_L

DeepSeek V3.1 Terminus

not listed

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

BF16

DeepSeek V3.1 Terminus

1373 GB1342.3 GB file

32K 1372 GB · 128K 1379 GB

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

How to run each

DeepSeek V3.1 Terminus

Ollama · Q4_K_M

$ollama run hf.co/unsloth/DeepSeek-V3.1-Terminus-GGUF:Q4_K_M

All ways to run DeepSeek V3.1 Terminus →

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 DeepSeek V3.1 Terminus and Qwen3.8 27B
Spec	DeepSeek V3.1 Terminus	Qwen3.8 27B
Publisher	DeepSeek	Alibaba
Parameters	684.5B	27.8B
Active parameters	40B per token	—
Architecture	DeepseekV3ForCausalLM	Qwen3_5ForConditionalGeneration
Context	160K tokens	256K tokens
Modalities	Chat, Function-calling	Vision, Function-calling
License	MIT	Apache 2.0
Released	Sep 2025	Aug 2026

Frequently Asked Questions

Which is better, DeepSeek V3.1 Terminus or Qwen3.8 27B?

Qwen3.8 27B leads llmrun Score 121.5 to 107.7; only Qwen3.8 27B fits 24 GB (Q4_K_M); DeepSeek V3.1 Terminus needs 189.7 GB even at its smallest quant. Choose DeepSeek V3.1 Terminus for also does chat; choose Qwen3.8 27B for higher llmrun Score and stronger at reasoning.

Which needs less VRAM, DeepSeek V3.1 Terminus or Qwen3.8 27B?

At Q4_K_M, DeepSeek V3.1 Terminus requires 414.6 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 DeepSeek V3.1 Terminus or Qwen3.8 27B on a 16 GB GPU?

DeepSeek V3.1 Terminus does not fit (smallest quant needs 189.7 GB); Qwen3.8 27B fits at Q3_K_L.

Which has a longer context window, DeepSeek V3.1 Terminus or Qwen3.8 27B?

DeepSeek V3.1 Terminus supports 163,840 tokens and Qwen3.8 27B supports 262,144 tokens.