DeepSeek V3.1 Terminus vs DeepSeek V3.2 Exp
DeepSeek V3.1 Terminus and DeepSeek V3.2 Exp match in llmrun Score, with values of 107.7 versus 109.0; neither fits 24 GB.
Model A · DeepSeek
DeepSeek V3.1 Terminus684.5B · 40.1B active · 160K context · MIT · Sep 2025
Model B · DeepSeek
DeepSeek V3.2 Exp685.4B · 41B active · 160K context · MIT · Sep 2025
Choose DeepSeek V3.2 Exp if you want…
Ahead on the benchmarks
4 of 5 shared boards
DeepSeek V3.1 Terminus: no clear edge over DeepSeek V3.2 Exp 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%.
8 GB
RTX 4060 · 8 GB tier
DeepSeek V3.1 Terminus
Doesn't fit
smallest quant needs 189.7 GB
DeepSeek V3.2 Exp
Doesn't fit
smallest quant needs 292.8 GB
12 GB
RTX 3060 12GB · 12 GB tier
DeepSeek V3.1 Terminus
Doesn't fit
smallest quant needs 189.7 GB
DeepSeek V3.2 Exp
Doesn't fit
smallest quant needs 292.8 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
DeepSeek V3.1 Terminus
Doesn't fit
smallest quant needs 189.7 GB
DeepSeek V3.2 Exp
Doesn't fit
smallest quant needs 292.8 GB
24 GBreference
RTX 4090 · 24 GB tier
DeepSeek V3.1 Terminus
Doesn't fit
smallest quant needs 189.7 GB
DeepSeek V3.2 Exp
Doesn't fit
smallest quant needs 292.8 GB
32 GB
RTX 5090 · 32 GB tier
DeepSeek V3.1 Terminus
Doesn't fit
smallest quant needs 189.7 GB
DeepSeek V3.2 Exp
Doesn't fit
smallest quant needs 292.8 GB
48 GB
RTX A6000 · 48 GB tier
DeepSeek V3.1 Terminus
Doesn't fit
smallest quant needs 189.7 GB
DeepSeek V3.2 Exp
Doesn't fit
smallest quant needs 292.8 GB
Mac 32 GB
Mac Mini M4 · Macs
DeepSeek V3.1 Terminus
Doesn't fit
smallest quant needs 189.7 GB
DeepSeek V3.2 Exp
Doesn't fit
smallest quant needs 292.8 GB
Mac 64 GB
Mac Studio M4 Max · Macs
DeepSeek V3.1 Terminus
Doesn't fit
smallest quant needs 189.7 GB
DeepSeek V3.2 Exp
Doesn't fit
smallest quant needs 292.8 GB
Mac 128 GB
Mac Studio M4 Max · Macs
DeepSeek V3.1 Terminus
Doesn't fit
smallest quant needs 189.7 GB
DeepSeek V3.2 Exp
Doesn't fit
smallest quant needs 292.8 GB
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
DeepSeek V3.1 Terminus
DeepSeek V3.2 Exp
Coding
DeepSeek V3.1 Terminus
DeepSeek V3.2 Exp
Science
DeepSeek V3.1 Terminus
DeepSeek V3.2 Exp
Reasoning
DeepSeek V3.1 Terminus
DeepSeek V3.2 Exp
DeepSeek V3.1 Terminus · #32 of 92 open models · #29 of 88 that fit ≤512 GB
DeepSeek V3.2 Exp · #27 of 92 open models · #24 of 88 that fit ≤512 GB
Benchmarks
5 shared boards: DeepSeek V3.1 Terminus leads 1, DeepSeek V3.2 Exp leads 4 · Benchmarks imported Oct 2026
DeepSeek V3.1 Terminus
1416.0#38/186 open
ArenaLMArena · Oct 2026
DeepSeek V3.2 Exp
1424.8#28/186 open
ArenaLMArena · Oct 2026
DeepSeek V3.1 Terminus
40.6%#28/65 open
Lab-reportedEpoch AI · Sep 2025
DeepSeek V3.2 Exp
38.9%#32/65 open
Lab-reportedEpoch AI · Sep 2025
DeepSeek V3.1 Terminus
1.7%#27/65 open
Lab-reportedEpoch AI · Sep 2025
DeepSeek V3.2 Exp
2.9%#25/65 open
Lab-reportedEpoch AI · Sep 2025
DeepSeek V3.1 Terminus
81.3%#21/68 open
Lab-reportedEpoch AI · Sep 2025
DeepSeek V3.2 Exp
87.7%#10/68 open
Lab-reportedEpoch AI · Sep 2025
DeepSeek V3.1 Terminus
28.6%#26/54 open
Lab-reportedEpoch AI · Sep 2025
DeepSeek V3.2 Exp
29.1%#24/54 open
Lab-reportedEpoch AI · Sep 2025
8 more boards (other shared and single-model boards)
Only DeepSeek V3.1 Terminus (1)
- ALE-Bench745.2
Only DeepSeek V3.2 Exp (7)
- LMArena WebDev1272.4
- Aider Polyglot74.2%
- WeirdML39.5%
- CL-bench13.2%
- CL-bench Life9.5%
- Fiction.LiveBench83.3%
- Vending-Bench 21034.0
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
DeepSeek V3.1 Terminus
295 GB245.7 GB file
32K 294 GB · 128K 300 GB
DeepSeek V3.2 Exp
295 GB~291.3 GB file
32K 294 GB · 128K 301 GB
Q3_K_S
DeepSeek V3.1 Terminus
303 GB290.4 GB file
32K 302 GB · 128K 309 GB
DeepSeek V3.2 Exp
not listed
Q3_K_M
DeepSeek V3.1 Terminus
338 GB320.5 GB file
32K 336 GB · 128K 343 GB
DeepSeek V3.2 Exp
338 GB~334.1 GB file
32K 337 GB · 128K 344 GB
Q4_0
DeepSeek V3.1 Terminus
346 GB380.1 GB file
32K 345 GB · 128K 352 GB
DeepSeek V3.2 Exp
not listed
Q4_K_M
DeepSeek V3.1 Terminus
415 GB405.4 GB file
32K 413 GB · 128K 420 GB
DeepSeek V3.2 Exp
415 GB~411.2 GB file
32K 414 GB · 128K 421 GB
Q5_K_M
DeepSeek V3.1 Terminus
492 GB476.2 GB file
32K 490 GB · 128K 497 GB
DeepSeek V3.2 Exp
492 GB~488.4 GB file
32K 491 GB · 128K 498 GB
Q6_K
DeepSeek V3.1 Terminus
569 GB551.3 GB file
32K 567 GB · 128K 574 GB
DeepSeek V3.2 Exp
569 GB~565.5 GB file
32K 568 GB · 128K 575 GB
Q8_0
DeepSeek V3.1 Terminus
688 GB713.3 GB file
32K 687 GB · 128K 694 GB
DeepSeek V3.2 Exp
689 GB~685.4 GB file
32K 688 GB · 128K 695 GB
14 more quants
IQ2_XXS
DeepSeek V3.1 Terminus
192 GB217.1 GB file
32K 191 GB · 128K 198 GB
DeepSeek V3.2 Exp
not listed
IQ2_XS
DeepSeek V3.1 Terminus
209 GB188.4 GB file
32K 208 GB · 128K 215 GB
DeepSeek V3.2 Exp
not listed
IQ2_S
DeepSeek V3.1 Terminus
218 GB189.6 GB file
32K 217 GB · 128K 223 GB
DeepSeek V3.2 Exp
not listed
IQ2_M
DeepSeek V3.1 Terminus
235 GB228.9 GB file
32K 234 GB · 128K 241 GB
DeepSeek V3.2 Exp
not listed
IQ3_XXS
DeepSeek V3.1 Terminus
269 GB273.5 GB file
32K 268 GB · 128K 275 GB
DeepSeek V3.2 Exp
not listed
IQ3_XS
DeepSeek V3.1 Terminus
286 GB277.1 GB file
32K 285 GB · 128K 292 GB
DeepSeek V3.2 Exp
not listed
IQ3_M
DeepSeek V3.1 Terminus
312 GB307.9 GB file
32K 311 GB · 128K 318 GB
DeepSeek V3.2 Exp
not listed
Q3_K_L
DeepSeek V3.1 Terminus
355 GB319.7 GB file
32K 353 GB · 128K 360 GB
DeepSeek V3.2 Exp
not listed
IQ4_XS
DeepSeek V3.1 Terminus
372 GB358.3 GB file
32K 371 GB · 128K 377 GB
DeepSeek V3.2 Exp
not listed
IQ4_NL
DeepSeek V3.1 Terminus
389 GB379.1 GB file
32K 388 GB · 128K 395 GB
DeepSeek V3.2 Exp
not listed
Q4_1
DeepSeek V3.1 Terminus
389 GB420.8 GB file
32K 388 GB · 128K 395 GB
DeepSeek V3.2 Exp
not listed
Q4_K_S
DeepSeek V3.1 Terminus
389 GB381.1 GB file
32K 388 GB · 128K 395 GB
DeepSeek V3.2 Exp
not listed
Q5_K_S
DeepSeek V3.1 Terminus
475 GB462.6 GB file
32K 473 GB · 128K 480 GB
DeepSeek V3.2 Exp
not listed
BF16
DeepSeek V3.1 Terminus
1373 GB1342.3 GB file
32K 1372 GB · 128K 1379 GB
DeepSeek V3.2 Exp
1375 GB~1370.8 GB file
32K 1373 GB · 128K 1380 GB
DeepSeek V3.1 Terminus
Ollama · Q4_K_M
ollama run hf.co/unsloth/DeepSeek-V3.1-Terminus-GGUF:Q4_K_MDeepSeek V3.2 Exp
No local recipe · Q4_K_M
No GGUF repo entry exists for this model yet.
All ways to run DeepSeek V3.2 Exp →| Spec | DeepSeek V3.1 Terminus | DeepSeek V3.2 Exp |
|---|---|---|
| Publisher | DeepSeek | DeepSeek |
| Parameters | 684.5B | 685.4B |
| Active parameters | 40B per token | 41B per token |
| Architecture | DeepseekV3ForCausalLM | DeepseekV32ForCausalLM |
| Context | 160K tokens | 160K tokens |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | MIT | MIT |
| Released | Sep 2025 | Sep 2025 |
Frequently Asked Questions
Which is better, DeepSeek V3.1 Terminus or DeepSeek V3.2 Exp?
DeepSeek V3.1 Terminus and DeepSeek V3.2 Exp match in llmrun Score, with values of 107.7 versus 109.0; neither fits 24 GB. Choose DeepSeek V3.2 Exp for ahead on the benchmarks.
Which needs less VRAM, DeepSeek V3.1 Terminus or DeepSeek V3.2 Exp?
At Q4_K_M, DeepSeek V3.1 Terminus requires 414.6 GB while DeepSeek V3.2 Exp needs 415.1 GB, making DeepSeek V3.1 Terminus the easier model to run on your local setup.
Can I run DeepSeek V3.1 Terminus or DeepSeek V3.2 Exp on a 16 GB GPU?
DeepSeek V3.1 Terminus does not fit (smallest quant needs 189.7 GB); DeepSeek V3.2 Exp does not fit (smallest quant needs 292.8 GB).
Which has a longer context window, DeepSeek V3.1 Terminus or DeepSeek V3.2 Exp?
DeepSeek V3.1 Terminus supports 163,840 tokens and DeepSeek V3.2 Exp supports 163,840 tokens.