DeepSeek V3.2 vs DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 leads llmrun Score 134.4 to 110.4; neither fits 24 GB.
Run DeepSeek V4.1 Flash 1017 in the cloud →
Model A · DeepSeek
DeepSeek V3.2685.4B · 41B active · 160K context · MIT · Dec 2025
Model B · DeepSeek
DeepSeek V4.1 Flash 1017763.2B · 16B active · 1M context · MIT · Oct 2026
Choose DeepSeek V3.2 if you want…
Also does chat
DeepSeek V4.1 Flash 1017 doesn't list it
Choose DeepSeek V4.1 Flash 1017 if you want…
Higher llmrun Score
134.4 vs 110.4
Stronger at agents
135.7 vs 108.1
Stronger at reasoning
137.1 vs 112.0
Ahead on the benchmarks
3 of 3 shared boards
Longer context window
1M vs 160K tokens
Also does vision
DeepSeek V3.2 doesn't list it
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 V3.2
Doesn't fit
smallest quant needs 189.9 GB
DeepSeek V4.1 Flash 1017
Doesn't fit
smallest quant needs 210.4 GB
12 GB
RTX 3060 12GB · 12 GB tier
DeepSeek V3.2
Doesn't fit
smallest quant needs 189.9 GB
DeepSeek V4.1 Flash 1017
Doesn't fit
smallest quant needs 210.4 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
DeepSeek V3.2
Doesn't fit
smallest quant needs 189.9 GB
DeepSeek V4.1 Flash 1017
Doesn't fit
smallest quant needs 210.4 GB
24 GBreference
RTX 4090 · 24 GB tier
DeepSeek V3.2
Doesn't fit
smallest quant needs 189.9 GB
DeepSeek V4.1 Flash 1017
Doesn't fit
smallest quant needs 210.4 GB
32 GB
RTX 5090 · 32 GB tier
DeepSeek V3.2
Doesn't fit
smallest quant needs 189.9 GB
DeepSeek V4.1 Flash 1017
Doesn't fit
smallest quant needs 210.4 GB
48 GB
RTX A6000 · 48 GB tier
DeepSeek V3.2
Doesn't fit
smallest quant needs 189.9 GB
DeepSeek V4.1 Flash 1017
Doesn't fit
smallest quant needs 210.4 GB
Mac 32 GB
Mac Mini M4 · Macs
DeepSeek V3.2
Doesn't fit
smallest quant needs 189.9 GB
DeepSeek V4.1 Flash 1017
Doesn't fit
smallest quant needs 210.4 GB
Mac 64 GB
Mac Studio M4 Max · Macs
DeepSeek V3.2
Doesn't fit
smallest quant needs 189.9 GB
DeepSeek V4.1 Flash 1017
Doesn't fit
smallest quant needs 210.4 GB
Mac 128 GB
Mac Studio M4 Max · Macs
DeepSeek V3.2
Doesn't fit
smallest quant needs 189.9 GB
DeepSeek V4.1 Flash 1017
Doesn't fit
smallest quant needs 210.4 GB
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
DeepSeek V3.2
DeepSeek V4.1 Flash 1017
Coding
DeepSeek V3.2
no data
DeepSeek V4.1 Flash 1017
Agents
DeepSeek V3.2
DeepSeek V4.1 Flash 1017
Math
DeepSeek V3.2
no data
DeepSeek V4.1 Flash 1017
Science
DeepSeek V3.2
no data
DeepSeek V4.1 Flash 1017
Reasoning
DeepSeek V3.2
DeepSeek V4.1 Flash 1017
DeepSeek V3.2 · #31 of 106 open models · #27 of 102 that fit ≤512 GB
DeepSeek V4.1 Flash 1017 · #2 of 106 open models · #1 of 102 that fit ≤512 GB
Benchmarks
3 shared boards: DeepSeek V3.2 leads 0, DeepSeek V4.1 Flash 1017 leads 3 · Benchmarks imported Nov 2026
DeepSeek V3.2
4.0%#16/22 open
IndependentEpoch AI · Dec 2025
DeepSeek V4.1 Flash 1017
78.1%#1/22 open
IndependentEpoch AI · Oct 2026
DeepSeek V3.2
57.0%#15/22 open
IndependentEpoch AI · Dec 2025
DeepSeek V4.1 Flash 1017
94.5%#2/22 open
IndependentEpoch AI · Oct 2026
DeepSeek V3.2
21.3%#19/20 open
Lab-reportedEpoch AI · Dec 2025
DeepSeek V4.1 Flash 1017
69.8%#1/20 open
Lab-reportedEpoch AI · Oct 2026
32 more boards (other shared and single-model boards)
DeepSeek V3.2
1362.5#36/55 open
ArenaLMArena · Oct 2026
DeepSeek V4.1 Flash 1017
1665.0#1/55 open
ArenaLMArena · Oct 2026
Only DeepSeek V3.2 (12)
- SWE-bench Verified70.0%
- LMArena Text1424.6
- Terminal-Bench39.6%
- MMLU-Pro85.0%
- SWE-bench Multilingual59.0%
- SWE-bench Bash Only60.0%
- SWE-bench Lite30.7%
- CL-bench12.4%
- CL-bench Life7.4%
- DTBench85.6%
- LMCA28.8%
- ProofBench8.0%
Only DeepSeek V4.1 Flash 1017 (19)
- GPQA Diamond93.2%
- AIME 2024/202599.4%
- FrontierMath71.2%
- SciCode55.9%
- SimpleQA42.5%
- FrontierMath Tier 446.3%
- Chess Puzzles46.0%
- CritPt24.0%
- LiveBench 2026 Reasoning89.1
- Mystery Game Puzzles49.0%
- LiveBench 2026 Browser76.0
- LiveBench 2026 Data Analysis79.5
- ALE-Bench1622.0
- CursorBench47.7%
- LiveBench 2026 Coding96.0
- LiveBench 2026 Long-Horizon50.9
- LiveBench 2026 Design83.4
- WeirdML v39.2%
- LiveBench 2026 Research79.5
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 V3.2
295 GB245.4 GB file
32K 294 GB · 128K 301 GB
DeepSeek V4.1 Flash 1017
325 GB264.5 GB file
32K 325 GB · 128K 326 GB
Q3_K_S
DeepSeek V3.2
304 GB290.4 GB file
32K 302 GB · 128K 309 GB
DeepSeek V4.1 Flash 1017
not listed
Q3_K_M
DeepSeek V3.2
338 GB320.2 GB file
32K 337 GB · 128K 344 GB
DeepSeek V4.1 Flash 1017
372 GB347.3 GB file
32K 373 GB · 128K 374 GB
Q4_0
DeepSeek V3.2
347 GB380.1 GB file
32K 345 GB · 128K 352 GB
DeepSeek V4.1 Flash 1017
not listed
Q4_K_M
DeepSeek V3.2
415 GB405.4 GB file
32K 414 GB · 128K 421 GB
DeepSeek V4.1 Flash 1017
458 GB444.7 GB file
32K 459 GB · 128K 460 GB
Q5_K_M
DeepSeek V3.2
492 GB476.2 GB file
32K 491 GB · 128K 498 GB
DeepSeek V4.1 Flash 1017
544 GB~543.8 GB file
32K 545 GB · 128K 546 GB
Q6_K
DeepSeek V3.2
569 GB551.3 GB file
32K 568 GB · 128K 575 GB
DeepSeek V4.1 Flash 1017
630 GB~629.6 GB file
32K 630 GB · 128K 632 GB
Q8_0
DeepSeek V3.2
689 GB713.3 GB file
32K 688 GB · 128K 695 GB
DeepSeek V4.1 Flash 1017
764 GB~763.2 GB file
32K 764 GB · 128K 765 GB
11 more quants
IQ2_XXS
DeepSeek V3.2
192 GB217.1 GB file
32K 191 GB · 128K 198 GB
DeepSeek V4.1 Flash 1017
210 GB300.5 GB file
32K 211 GB · 128K 212 GB
IQ2_XS
DeepSeek V3.2
not listed
DeepSeek V4.1 Flash 1017
229 GB~229.0 GB file
32K 230 GB · 128K 231 GB
IQ2_M
DeepSeek V3.2
235 GB228.1 GB file
32K 234 GB · 128K 241 GB
DeepSeek V4.1 Flash 1017
not listed
IQ3_XXS
DeepSeek V3.2
269 GB273.1 GB file
32K 268 GB · 128K 275 GB
DeepSeek V4.1 Flash 1017
296 GB394.7 GB file
32K 296 GB · 128K 298 GB
IQ3_S
DeepSeek V3.2
not listed
DeepSeek V4.1 Flash 1017
325 GB423.6 GB file
32K 325 GB · 128K 326 GB
IQ4_XS
DeepSeek V3.2
372 GB358.3 GB file
32K 371 GB · 128K 378 GB
DeepSeek V4.1 Flash 1017
not listed
IQ4_NL
DeepSeek V3.2
389 GB379.1 GB file
32K 388 GB · 128K 395 GB
DeepSeek V4.1 Flash 1017
not listed
Q4_1
DeepSeek V3.2
389 GB420.8 GB file
32K 388 GB · 128K 395 GB
DeepSeek V4.1 Flash 1017
not listed
Q4_K_S
DeepSeek V3.2
389 GB381.1 GB file
32K 388 GB · 128K 395 GB
DeepSeek V4.1 Flash 1017
not listed
Q5_K_S
DeepSeek V3.2
475 GB462.6 GB file
32K 474 GB · 128K 481 GB
DeepSeek V4.1 Flash 1017
not listed
BF16
DeepSeek V3.2
1375 GB1342.3 GB file
32K 1373 GB · 128K 1380 GB
DeepSeek V4.1 Flash 1017
1527 GB~1526.4 GB file
32K 1527 GB · 128K 1528 GB
DeepSeek V3.2
Ollama · Q4_K_M
ollama run hf.co/unsloth/DeepSeek-V3.2-GGUF:Q4_K_MDeepSeek V4.1 Flash 1017
Ollama · Q4_K_M
ollama run hf.co/mrfakename/DeepSeek-V4.1-Flash-1017-GGUF:Q4_K_M| Spec | DeepSeek V3.2 | DeepSeek V4.1 Flash 1017 |
|---|---|---|
| Publisher | DeepSeek | DeepSeek |
| Parameters | 685.4B | 763.2B |
| Active parameters | 41B per token | 16B per token |
| Architecture | DeepseekV32ForCausalLM | DeepseekV41ForCausalLM |
| Context | 160K tokens | 1M tokens |
| Modalities | Chat | Vision |
| License | MIT | MIT |
| Released | Dec 2025 | Oct 2026 |
Frequently Asked Questions
Which is better, DeepSeek V3.2 or DeepSeek V4.1 Flash 1017?
DeepSeek V4.1 Flash 1017 leads llmrun Score 134.4 to 110.4; neither fits 24 GB. Choose DeepSeek V3.2 for also does chat; choose DeepSeek V4.1 Flash 1017 for higher llmrun Score and stronger at agents.
Which needs less VRAM, DeepSeek V3.2 or DeepSeek V4.1 Flash 1017?
At Q4_K_M, DeepSeek V3.2 requires 415.1 GB while DeepSeek V4.1 Flash 1017 needs 458.3 GB, making DeepSeek V3.2 the easier model to run on your local setup.
Can I run DeepSeek V3.2 or DeepSeek V4.1 Flash 1017 on a 16 GB GPU?
DeepSeek V3.2 does not fit (smallest quant needs 189.9 GB); DeepSeek V4.1 Flash 1017 does not fit (smallest quant needs 210.4 GB).
Which has a longer context window, DeepSeek V3.2 or DeepSeek V4.1 Flash 1017?
DeepSeek V3.2 supports 163,840 tokens and DeepSeek V4.1 Flash 1017 supports 1,048,576 tokens.