DeepSeek V4.1 Flash vs Inkling
DeepSeek V4.1 Flash leads llmrun Score 129.5 to 116.0; neither fits 24 GB.
Model A · DeepSeek
DeepSeek V4.1 Flash763.2B · 188B active · 1M context · MIT · Sep 2026
Model B · Thinking Machines
Inkling952.4B · 18.1B active · Apache 2.0 · Jul 2026
Choose DeepSeek V4.1 Flash if you want…
Higher llmrun Score
129.5 vs 116.0
Stronger at math
129.0 vs 112.1
Stronger at agents
127.9 vs 111.4
Ahead on the benchmarks
22 of 22 shared boards
Lighter on memory
458.3 vs 572.1 GB at Q4_K_M
Choose Inkling if you want…
Also does chat
DeepSeek V4.1 Flash 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 V4.1 Flash
Doesn't fit
smallest quant needs 210.4 GB
Inkling
Doesn't fit
smallest quant needs 408.4 GB
12 GB
RTX 3060 12GB · 12 GB tier
DeepSeek V4.1 Flash
Doesn't fit
smallest quant needs 210.4 GB
Inkling
Doesn't fit
smallest quant needs 408.4 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
DeepSeek V4.1 Flash
Doesn't fit
smallest quant needs 210.4 GB
Inkling
Doesn't fit
smallest quant needs 408.4 GB
24 GBreference
RTX 4090 · 24 GB tier
DeepSeek V4.1 Flash
Doesn't fit
smallest quant needs 210.4 GB
Inkling
Doesn't fit
smallest quant needs 408.4 GB
32 GB
RTX 5090 · 32 GB tier
DeepSeek V4.1 Flash
Doesn't fit
smallest quant needs 210.4 GB
Inkling
Doesn't fit
smallest quant needs 408.4 GB
48 GB
RTX A6000 · 48 GB tier
DeepSeek V4.1 Flash
Doesn't fit
smallest quant needs 210.4 GB
Inkling
Doesn't fit
smallest quant needs 408.4 GB
Mac 32 GB
Mac Mini M4 · Macs
DeepSeek V4.1 Flash
Doesn't fit
smallest quant needs 210.4 GB
Inkling
Doesn't fit
smallest quant needs 408.4 GB
Mac 64 GB
Mac Studio M4 Max · Macs
DeepSeek V4.1 Flash
Doesn't fit
smallest quant needs 210.4 GB
Inkling
Doesn't fit
smallest quant needs 408.4 GB
Mac 128 GB
Mac Studio M4 Max · Macs
DeepSeek V4.1 Flash
Doesn't fit
smallest quant needs 210.4 GB
Inkling
Doesn't fit
smallest quant needs 408.4 GB
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
DeepSeek V4.1 Flash
Inkling
Coding
DeepSeek V4.1 Flash
Inkling
Agents
DeepSeek V4.1 Flash
Inkling
Math
DeepSeek V4.1 Flash
Inkling
Science
DeepSeek V4.1 Flash
Inkling
Reasoning
DeepSeek V4.1 Flash
Inkling
DeepSeek V4.1 Flash · #5 of 100 open models · #4 of 96 that fit ≤512 GB
Inkling · #18 of 100 open models · #15 of 96 that fit ≤640 GB
Benchmarks
22 shared boards: DeepSeek V4.1 Flash leads 22, Inkling leads 0 · Benchmarks imported Oct 2026
DeepSeek V4.1 Flash
89.8%#11/98 open
IndependentEpoch AI · Sep 2026
Inkling
88.3%#14/98 open
IndependentEpoch AI · Jul 2026
DeepSeek V4.1 Flash
80.0#2/19 open
IndependentLiveBench · Jun 2026
Inkling
71.0#14/19 open
IndependentLiveBench · Jun 2026
DeepSeek V4.1 Flash
86.7#3/19 open
IndependentLiveBench · Jun 2026
Inkling
78.3#14/19 open
IndependentLiveBench · Jun 2026
DeepSeek V4.1 Flash
98.3%#2/86 open
IndependentEpoch AI · Sep 2026
Inkling
88.9%#17/86 open
IndependentEpoch AI · Jul 2026
DeepSeek V4.1 Flash
67.4%#4/17 open
IndependentEpoch AI · Sep 2026
Inkling
33.3%#15/17 open
IndependentEpoch AI · Jul 2026
DeepSeek V4.1 Flash
93.3#2/19 open
IndependentLiveBench · Jun 2026
Inkling
88.4#7/19 open
IndependentLiveBench · Jun 2026
DeepSeek V4.1 Flash
72.9%#1/19 open
IndependentEpoch AI · Sep 2026
Inkling
36.5%#8/19 open
IndependentEpoch AI · Jul 2026
DeepSeek V4.1 Flash
51.8%#5/66 open
Lab-reportedEpoch AI · Sep 2026
Inkling
47.0%#18/66 open
Lab-reportedEpoch AI · Jul 2026
DeepSeek V4.1 Flash
94.5%#1/19 open
IndependentEpoch AI · Sep 2026
Inkling
79.5%#8/19 open
IndependentEpoch AI · Jul 2026
DeepSeek V4.1 Flash
42.9%#5/17 open
IndependentEpoch AI · Sep 2026
Inkling
40.3%#8/17 open
IndependentEpoch AI · Jul 2026
24 more boards (other shared and single-model boards)
DeepSeek V4.1 Flash
26.8%#5/13 open
IndependentEpoch AI · Sep 2026
Inkling
4.9%#12/13 open
IndependentEpoch AI · Jul 2026
DeepSeek V4.1 Flash
43.9%#2/12 open
Lab-reportedEpoch AI · Sep 2026
Inkling
14.0%#11/12 open
Lab-reportedEpoch AI · Jul 2026
DeepSeek V4.1 Flash
1092.3#8/43 open
Lab-reportedEpoch AI · Sep 2026
Inkling
946.0#11/43 open
Lab-reportedEpoch AI · Jul 2026
DeepSeek V4.1 Flash
39.5%#9/16 open
Lab-reportedEpoch AI · Sep 2026
Inkling
33.8%#12/16 open
Lab-reportedEpoch AI · Jul 2026
DeepSeek V4.1 Flash
48.0%#1/14 open
IndependentEpoch AI · Sep 2026
Inkling
21.0%#7/14 open
IndependentEpoch AI · Jul 2026
DeepSeek V4.1 Flash
14.3%#8/66 open
Lab-reportedEpoch AI · Sep 2026
Inkling
5.4%#16/66 open
Lab-reportedEpoch AI · Jul 2026
DeepSeek V4.1 Flash
89.9%#8/68 open
Lab-reportedEpoch AI · Sep 2026
Inkling
87.5%#13/68 open
Lab-reportedEpoch AI · Jul 2026
DeepSeek V4.1 Flash
85.4#2/15 open
IndependentLiveBench · Sep 2026
Inkling
64.0#9/15 open
IndependentLiveBench · Sep 2026
DeepSeek V4.1 Flash
43.8#2/15 open
IndependentLiveBench · Sep 2026
Inkling
14.1#11/15 open
IndependentLiveBench · Sep 2026
DeepSeek V4.1 Flash
86.7#2/15 open
IndependentLiveBench · Sep 2026
Inkling
78.3#9/15 open
IndependentLiveBench · Sep 2026
DeepSeek V4.1 Flash
47.0%#3/54 open
Lab-reportedEpoch AI · Sep 2026
Inkling
37.6%#11/54 open
Lab-reportedEpoch AI · Jul 2026
DeepSeek V4.1 Flash
54.0%#6/26 open
Lab-reportedEpoch AI · Sep 2026
Inkling
0.0%#26/26 open
Lab-reportedEpoch AI · Jul 2026
DeepSeek V4.1 Flash
1474.6#5/187 open
ArenaLMArena · Oct 2026
Inkling
1440.9#20/187 open
ArenaLMArena · Oct 2026
DeepSeek V4.1 Flash
1618.4#7/52 open
ArenaLMArena · Oct 2026
Inkling
1413.7#26/52 open
ArenaLMArena · Oct 2026
DeepSeek V4.1 Flash
80.0#3/15 open
IndependentLiveBench · Sep 2026
Inkling
16.0#8/15 open
IndependentLiveBench · Sep 2026
DeepSeek V4.1 Flash
79.3#2/15 open
IndependentLiveBench · Sep 2026
Inkling
72.8#8/15 open
IndependentLiveBench · Sep 2026
DeepSeek V4.1 Flash
77.0#5/15 open
IndependentLiveBench · Sep 2026
Inkling
58.3#14/15 open
IndependentLiveBench · Sep 2026
DeepSeek V4.1 Flash
85.3#1/15 open
IndependentLiveBench · Sep 2026
Inkling
59.9#11/15 open
IndependentLiveBench · Sep 2026
Only DeepSeek V4.1 Flash (3)
- Furniture Assembly34.2%
- Mystery Game Puzzles43.0%
- Surface Evolver Bench46.3%
Only Inkling (3)
- SimpleBench50.0%
- WeirdML32.3%
- FrontierSWE4.1%
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 V4.1 Flash
325 GB264.5 GB file
32K 325 GB · 128K 326 GB
Inkling
405 GB~404.8 GB file
32K 412 GB · 128K 432 GB
Q3_K_M
DeepSeek V4.1 Flash
372 GB347.3 GB file
32K 373 GB · 128K 374 GB
Inkling
465 GB~464.3 GB file
32K 471 GB · 128K 491 GB
Q4_K_M
DeepSeek V4.1 Flash
458 GB444.7 GB file
32K 459 GB · 128K 460 GB
Inkling
572 GB~571.4 GB file
32K 578 GB · 128K 598 GB
Q5_K_M
DeepSeek V4.1 Flash
544 GB~543.8 GB file
32K 545 GB · 128K 546 GB
Inkling
679 GB~678.6 GB file
32K 686 GB · 128K 705 GB
Q6_K
DeepSeek V4.1 Flash
630 GB~629.6 GB file
32K 630 GB · 128K 632 GB
Inkling
786 GB~785.7 GB file
32K 793 GB · 128K 813 GB
Q8_0
DeepSeek V4.1 Flash
764 GB508.0 GB file
32K 764 GB · 128K 765 GB
Inkling
953 GB856.8 GB file
32K 959 GB · 128K 979 GB
3 more quants
IQ2_XXS
DeepSeek V4.1 Flash
210 GB~209.9 GB file
32K 211 GB · 128K 212 GB
Inkling
not listed
IQ3_XS
DeepSeek V4.1 Flash
315 GB434.0 GB file
32K 316 GB · 128K 317 GB
Inkling
not listed
BF16
DeepSeek V4.1 Flash
1527 GB~1526.4 GB file
32K 1527 GB · 128K 1528 GB
Inkling
1905 GB1894.3 GB file
32K 1912 GB · 128K 1932 GB
DeepSeek V4.1 Flash
Ollama · Q4_K_M
ollama run hf.co/vcruz305/DeepSeek-V4.1-Flash-GGUF:Q4_K_MInkling
Ollama · Q4_K_M
ollama run hf.co/unsloth/inkling-GGUF| Spec | DeepSeek V4.1 Flash | Inkling |
|---|---|---|
| Publisher | DeepSeek | Thinking Machines |
| Parameters | 763.2B | 952.4B |
| Active parameters | 188B per token | 18B per token |
| Architecture | DeepseekV41ForCausalLM | InklingForConditionalGeneration |
| Context | 1M tokens | — |
| Modalities | Vision, Function-calling | Vision, Chat, Function-calling |
| License | MIT | Apache 2.0 |
| Released | Sep 2026 | Jul 2026 |
Frequently Asked Questions
Which is better, DeepSeek V4.1 Flash or Inkling?
DeepSeek V4.1 Flash leads llmrun Score 129.5 to 116.0; neither fits 24 GB. Choose DeepSeek V4.1 Flash for higher llmrun Score and stronger at math; choose Inkling for also does chat.
Which needs less VRAM, DeepSeek V4.1 Flash or Inkling?
At Q4_K_M, DeepSeek V4.1 Flash requires 458.3 GB while Inkling needs 572.1 GB, making DeepSeek V4.1 Flash the easier model to run on your local setup.
Can I run DeepSeek V4.1 Flash or Inkling on a 16 GB GPU?
DeepSeek V4.1 Flash does not fit (smallest quant needs 210.4 GB); Inkling does not fit (smallest quant needs 408.4 GB).