DeepSeek V4.1 Flash 1017 vs MiMo V2.6 Pro RL

DeepSeek V4.1 Flash 1017 and MiMo V2.6 Pro RL match in llmrun Score, with values of 133.2 versus 133.2; neither fits 24 GB.

Model A · DeepSeek

DeepSeek V4.1 Flash 1017

133.2llmrun Score

763.2B · 16B active · 1M context · MIT · Oct 2026

Vision

Model B · Xiaomi

MiMo V2.6 Pro RL

133.2llmrun Score

1020B · 42B active · 1M context · MIT · Sep 2026

ChatFunctions

Which should you choose?

Choose DeepSeek V4.1 Flash 1017 if you want…

Ahead on the benchmarks
3 of 3 shared boards
Lighter on memory
458.3 vs 612.5 GB at Q4_K_M
Also does vision
MiMo V2.6 Pro RL doesn't list it

Choose MiMo V2.6 Pro RL if you want…

Also does chat, function-calling
DeepSeek V4.1 Flash 1017 doesn't list it

On your hardware

Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.

MemoryDeepSeek V4.1 Flash 1017MiMo V2.6 Pro RL

8 GB

RTX 4060 · 8 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

12 GB

RTX 3060 12GB · 12 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

24 GBreference

RTX 4090 · 24 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

32 GB

RTX 5090 · 32 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

48 GB

RTX A6000 · 48 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 32 GB

Mac Mini M4 · Macs

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 64 GB

Mac Studio M4 Max · Macs

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 128 GB

Mac Studio M4 Max · Macs

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

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 V4.1 Flash 1017 MiMo V2.6 Pro RL

Overall

DeepSeek V4.1 Flash 1017

133.2131–136

MiMo V2.6 Pro RL

133.2130–136

Coding

DeepSeek V4.1 Flash 1017

no data

MiMo V2.6 Pro RL

125.1118–132

Agents

DeepSeek V4.1 Flash 1017

no data

MiMo V2.6 Pro RL

131.2126–137

Math

DeepSeek V4.1 Flash 1017

132.0129–135

MiMo V2.6 Pro RL

no data

Science

DeepSeek V4.1 Flash 1017

no data

MiMo V2.6 Pro RL

139.6128–151

Reasoning

DeepSeek V4.1 Flash 1017

139.8133–146

MiMo V2.6 Pro RL

no data

DeepSeek V4.1 Flash 1017 · #1 of 101 open models · #1 of 98 that fit ≤512 GB

MiMo V2.6 Pro RL · #2 of 101 open models · #2 of 98 that fit ≤640 GB

Benchmarks

3 shared boards: DeepSeek V4.1 Flash 1017 leads 3, MiMo V2.6 Pro RL leads 0 · Benchmarks imported Oct 2026

BoardDeepSeek V4.1 Flash 1017MiMo V2.6 Pro RL

LiveBench 2026 Coding

DeepSeek V4.1 Flash 1017

96.0#1/17 open

IndependentLiveBench · Oct 2026

MiMo V2.6 Pro RL

81.5#6/17 open

IndependentLiveBench · Oct 2026

LiveBench 2026 Long-Horizon

DeepSeek V4.1 Flash 1017

50.9#1/17 open

IndependentLiveBench · Oct 2026

MiMo V2.6 Pro RL

47.5#2/17 open

IndependentLiveBench · Oct 2026

LiveBench 2026 Reasoning

DeepSeek V4.1 Flash 1017

89.1#2/17 open

IndependentLiveBench · Oct 2026

MiMo V2.6 Pro RL

79.6#8/17 open

IndependentLiveBench · Oct 2026

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

LMArena WebDev

DeepSeek V4.1 Flash 1017

1665.0#1/55 open

ArenaLMArena · Oct 2026

MiMo V2.6 Pro RL

1625.4#6/55 open

ArenaLMArena · Oct 2026

LiveBench 2026 Browser

DeepSeek V4.1 Flash 1017

76.0#5/17 open

IndependentLiveBench · Oct 2026

MiMo V2.6 Pro RL

88.0#2/17 open

IndependentLiveBench · Oct 2026

LiveBench 2026 Data Analysis

DeepSeek V4.1 Flash 1017

79.5#1/17 open

IndependentLiveBench · Oct 2026

MiMo V2.6 Pro RL

72.3#9/17 open

IndependentLiveBench · Oct 2026

LiveBench 2026 Design

DeepSeek V4.1 Flash 1017

83.4#1/17 open

IndependentLiveBench · Oct 2026

MiMo V2.6 Pro RL

78.5#3/17 open

IndependentLiveBench · Oct 2026

LiveBench 2026 Research

DeepSeek V4.1 Flash 1017

79.5#3/17 open

IndependentLiveBench · Oct 2026

MiMo V2.6 Pro RL

76.7#6/17 open

IndependentLiveBench · Oct 2026

Only DeepSeek V4.1 Flash 1017 (7)

Only MiMo V2.6 Pro RL (6)

LMArena Text1479.5
SciCode60.9%
APEX-Agents54.4%
CritPt26.6%
ALE-Bench1158.1
ProofBench70.0%

VRAM by quantization

Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.

QuantDeepSeek V4.1 Flash 1017MiMo V2.6 Pro RL

Q2_K

DeepSeek V4.1 Flash 1017

325 GB264.5 GB file

32K 325 GB · 128K 326 GB

MiMo V2.6 Pro RL

434 GB418.8 GB file

32K 437 GB · 128K 448 GB

Q3_K_M

DeepSeek V4.1 Flash 1017

372 GB347.3 GB file

32K 373 GB · 128K 374 GB

MiMo V2.6 Pro RL

498 GB~497.3 GB file

32K 501 GB · 128K 512 GB

Q4_0

DeepSeek V4.1 Flash 1017

not listed

MiMo V2.6 Pro RL

511 GB~510.0 GB file

32K 514 GB · 128K 524 GB

Q4_K_M

DeepSeek V4.1 Flash 1017

458 GB444.7 GB file

32K 459 GB · 128K 460 GB

MiMo V2.6 Pro RL

613 GB~612.0 GB file

32K 616 GB · 128K 626 GB

Q5_K_M

DeepSeek V4.1 Flash 1017

544 GB~543.8 GB file

32K 545 GB · 128K 546 GB

MiMo V2.6 Pro RL

727 GB~726.8 GB file

32K 731 GB · 128K 741 GB

Q6_K

DeepSeek V4.1 Flash 1017

630 GB~629.6 GB file

32K 630 GB · 128K 632 GB

MiMo V2.6 Pro RL

842 GB~841.5 GB file

32K 845 GB · 128K 856 GB

Q8_0

DeepSeek V4.1 Flash 1017

764 GB~763.2 GB file

32K 764 GB · 128K 765 GB

MiMo V2.6 Pro RL

1021 GB~1020.0 GB file

32K 1024 GB · 128K 1034 GB

5 more quants

IQ2_XXS

DeepSeek V4.1 Flash 1017

210 GB300.5 GB file

32K 211 GB · 128K 212 GB

MiMo V2.6 Pro RL

not listed

IQ2_XS

DeepSeek V4.1 Flash 1017

229 GB~229.0 GB file

32K 230 GB · 128K 231 GB

MiMo V2.6 Pro RL

not listed

IQ3_XXS

DeepSeek V4.1 Flash 1017

296 GB394.7 GB file

32K 296 GB · 128K 298 GB

MiMo V2.6 Pro RL

not listed

IQ3_S

DeepSeek V4.1 Flash 1017

325 GB423.6 GB file

32K 325 GB · 128K 326 GB

MiMo V2.6 Pro RL

not listed

BF16

DeepSeek V4.1 Flash 1017

1527 GB~1526.4 GB file

32K 1527 GB · 128K 1528 GB

MiMo V2.6 Pro RL

2041 GB~2040.0 GB file

32K 2044 GB · 128K 2054 GB

How to run each

DeepSeek V4.1 Flash 1017

Ollama · Q4_K_M

$ollama run hf.co/mrfakename/DeepSeek-V4.1-Flash-1017-GGUF:Q4_K_M

All ways to run DeepSeek V4.1 Flash 1017 →

MiMo V2.6 Pro RL

Ollama · Q4_K_M

$ollama run hf.co/ggml-org/MiMo-V2.6-Pro-RL-GGUF

All ways to run MiMo V2.6 Pro RL →

Specifications

Specifications of DeepSeek V4.1 Flash 1017 and MiMo V2.6 Pro RL
Spec	DeepSeek V4.1 Flash 1017	MiMo V2.6 Pro RL
Publisher	DeepSeek	Xiaomi
Parameters	763.2B	1020B
Active parameters	16B per token	42B per token
Architecture	DeepseekV41ForCausalLM	MiMoV2ForCausalLM
Context	1M tokens	1M tokens
Modalities	Vision	Chat, Function-calling
License	MIT	MIT
Released	Oct 2026	Sep 2026

Frequently Asked Questions

Which is better, DeepSeek V4.1 Flash 1017 or MiMo V2.6 Pro RL?

DeepSeek V4.1 Flash 1017 and MiMo V2.6 Pro RL match in llmrun Score, with values of 133.2 versus 133.2; neither fits 24 GB. Choose DeepSeek V4.1 Flash 1017 for ahead on the benchmarks and lighter on memory; choose MiMo V2.6 Pro RL for also does chat, function-calling.

Which needs less VRAM, DeepSeek V4.1 Flash 1017 or MiMo V2.6 Pro RL?

At Q4_K_M, DeepSeek V4.1 Flash 1017 requires 458.3 GB while MiMo V2.6 Pro RL needs 612.5 GB, making DeepSeek V4.1 Flash 1017 the easier model to run on your local setup.

Can I run DeepSeek V4.1 Flash 1017 or MiMo V2.6 Pro RL on a 16 GB GPU?

DeepSeek V4.1 Flash 1017 does not fit (smallest quant needs 210.4 GB); MiMo V2.6 Pro RL does not fit (smallest quant needs 435.6 GB).

Which has a longer context window, DeepSeek V4.1 Flash 1017 or MiMo V2.6 Pro RL?

DeepSeek V4.1 Flash 1017 supports 1,048,576 tokens and MiMo V2.6 Pro RL supports 1,048,576 tokens.