DeepSeek V4 Flash vs MiMo V2.6 Flash RL

MiMo V2.6 Flash RL leads llmrun Score 131.9 to 109.3; neither fits 24 GB.

Model A · DeepSeek

DeepSeek V4 Flash

109.3llmrun Score

290.9B · 14.1B active · 1M context · MIT · Apr 2026

Chat

Model B · Xiaomi

MiMo V2.6 Flash RL

131.9llmrun Score

309B · 15B active · 1M context · MIT · Sep 2026

ChatFunctions

Which should you choose?

Choose DeepSeek V4 Flash if you want…

Fits a Mac 128 GB
IQ3_S · 124.1 GB; MiMo V2.6 Flash RL needs 93.8 GB at its smallest quant

Choose MiMo V2.6 Flash RL if you want…

Higher llmrun Score
131.9 vs 109.3
Stronger at coding
123.7 vs 106.6
Stronger at science
121.8 vs 111.4
Ahead on the benchmarks
3 of 3 shared boards
Also does function-calling
DeepSeek V4 Flash doesn't list it
Newer release
Sep 2026 vs Apr 2026

On your hardware

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

MemoryDeepSeek V4 FlashMiMo V2.6 Flash RL

8 GB

RTX 4060 · 8 GB tier

DeepSeek V4 Flash

Doesn't fit

smallest quant needs 80.5 GB

MiMo V2.6 Flash RL

Doesn't fit

smallest quant needs 93.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

DeepSeek V4 Flash

Doesn't fit

smallest quant needs 80.5 GB

MiMo V2.6 Flash RL

Doesn't fit

smallest quant needs 93.8 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

DeepSeek V4 Flash

Doesn't fit

smallest quant needs 80.5 GB

MiMo V2.6 Flash RL

Doesn't fit

smallest quant needs 93.8 GB

24 GBreference

RTX 4090 · 24 GB tier

DeepSeek V4 Flash

Doesn't fit

smallest quant needs 80.5 GB

MiMo V2.6 Flash RL

Doesn't fit

smallest quant needs 93.8 GB

32 GB

RTX 5090 · 32 GB tier

DeepSeek V4 Flash

Doesn't fit

smallest quant needs 80.5 GB

MiMo V2.6 Flash RL

Doesn't fit

smallest quant needs 93.8 GB

48 GB

RTX A6000 · 48 GB tier

DeepSeek V4 Flash

Doesn't fit

smallest quant needs 80.5 GB

MiMo V2.6 Flash RL

Doesn't fit

smallest quant needs 93.8 GB

Mac 32 GB

Mac Mini M4 · Macs

DeepSeek V4 Flash

Doesn't fit

smallest quant needs 80.5 GB

MiMo V2.6 Flash RL

Doesn't fit

smallest quant needs 93.8 GB

Mac 64 GB

Mac Studio M4 Max · Macs

DeepSeek V4 Flash

Doesn't fit

smallest quant needs 80.5 GB

MiMo V2.6 Flash RL

Doesn't fit

smallest quant needs 93.8 GB

Mac 128 GB

Mac Studio M4 Max · Macs

DeepSeek V4 Flash

IQ3_S · ~41 tok/s

124.1 GB · up to 32Kbetter quant

MiMo V2.6 Flash RL

IQ2_M · ~44 tok/s

105.4 GB · up to 256K

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 Flash MiMo V2.6 Flash RL

Overall

DeepSeek V4 Flash

109.3104–114

MiMo V2.6 Flash RL

131.9129–135

Coding

DeepSeek V4 Flash

106.699–115

MiMo V2.6 Flash RL

123.7115–133

Science

DeepSeek V4 Flash

111.493–130

MiMo V2.6 Flash RL

121.8106–138

Reasoning

DeepSeek V4 Flash

111.8105–119

MiMo V2.6 Flash RL

no data

DeepSeek V4 Flash · #28 of 100 open models · #13 of 78 that fit ≤192 GB

MiMo V2.6 Flash RL · #3 of 100 open models · #1 of 78 that fit ≤192 GB

Benchmarks

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

BoardDeepSeek V4 FlashMiMo V2.6 Flash RL

SciCode

DeepSeek V4 Flash

44.9%#23/66 open

Lab-reportedEpoch AI · Apr 2026

MiMo V2.6 Flash RL

51.3%#7/66 open

Lab-reportedEpoch AI · Sep 2026

ALE-Bench

DeepSeek V4 Flash

678.2#23/43 open

Lab-reportedEpoch AI · Apr 2026

MiMo V2.6 Flash RL

1244.2#5/43 open

Lab-reportedEpoch AI · Sep 2026

CritPt

DeepSeek V4 Flash

7.1%#14/66 open

Lab-reportedEpoch AI · Apr 2026

MiMo V2.6 Flash RL

12.0%#10/66 open

Lab-reportedEpoch AI · Sep 2026

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

LMArena Text

DeepSeek V4 Flash

1438.7#21/187 open

ArenaLMArena · Oct 2026

MiMo V2.6 Flash RL

1450.9#15/187 open

ArenaLMArena · Oct 2026

LMArena WebDev

DeepSeek V4 Flash

1581.4#12/52 open

ArenaLMArena · Oct 2026

MiMo V2.6 Flash RL

1634.3#2/52 open

ArenaLMArena · Oct 2026

Only DeepSeek V4 Flash (7)

Only MiMo V2.6 Flash RL (1)

ProofBench63.0%

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 FlashMiMo V2.6 Flash RL

Q2_K

DeepSeek V4 Flash

124 GB107.0 GB file

32K 124 GB · 128K 125 GB

MiMo V2.6 Flash RL

132 GB126.4 GB file

32K 133 GB · 128K 138 GB

Q3_K_M

DeepSeek V4 Flash

142 GB129.3 GB file

32K 143 GB · 128K 144 GB

MiMo V2.6 Flash RL

151 GB~150.6 GB file

32K 153 GB · 128K 157 GB

Q4_0

DeepSeek V4 Flash

not listed

MiMo V2.6 Flash RL

155 GB~154.5 GB file

32K 156 GB · 128K 161 GB

Q4_K_M

DeepSeek V4 Flash

175 GB174.9 GB file

32K 175 GB · 128K 176 GB

MiMo V2.6 Flash RL

186 GB~185.4 GB file

32K 187 GB · 128K 192 GB

Q5_K_M

DeepSeek V4 Flash

208 GB~207.3 GB file

32K 208 GB · 128K 209 GB

MiMo V2.6 Flash RL

221 GB~220.2 GB file

32K 222 GB · 128K 227 GB

Q6_K

DeepSeek V4 Flash

240 GB~240.0 GB file

32K 241 GB · 128K 242 GB

MiMo V2.6 Flash RL

255 GB~254.9 GB file

32K 257 GB · 128K 262 GB

Q8_0

DeepSeek V4 Flash

291 GB302.3 GB file

32K 292 GB · 128K 293 GB

MiMo V2.6 Flash RL

309 GB~309.0 GB file

32K 311 GB · 128K 316 GB

10 more quants

IQ2_XXS

DeepSeek V4 Flash

80.3 GB90.9 GB file

32K 80.7 GB · 128K 81.8 GB

MiMo V2.6 Flash RL

not listed

IQ2_XS

DeepSeek V4 Flash

87.6 GB87.0 GB file

32K 88.0 GB · 128K 89.0 GB

MiMo V2.6 Flash RL

93.1 GB98.7 GB file

32K 94.6 GB · 128K 99.4 GB

IQ2_S

DeepSeek V4 Flash

91.2 GB88.0 GB file

32K 91.6 GB · 128K 92.7 GB

MiMo V2.6 Flash RL

not listed

IQ2_M

DeepSeek V4 Flash

98.5 GB90.9 GB file

32K 98.9 GB · 128K 99.9 GB

MiMo V2.6 Flash RL

105 GB107.8 GB file

32K 106 GB · 128K 111 GB

IQ3_XXS

DeepSeek V4 Flash

113 GB103.0 GB file

32K 113 GB · 128K 114 GB

MiMo V2.6 Flash RL

not listed

Q2_K_S

DeepSeek V4 Flash

117 GB98.6 GB file

32K 117 GB · 128K 118 GB

MiMo V2.6 Flash RL

not listed

IQ3_S

DeepSeek V4 Flash

124 GB117.3 GB file

32K 124 GB · 128K 125 GB

MiMo V2.6 Flash RL

not listed

IQ4_XS

DeepSeek V4 Flash

157 GB137.9 GB file

32K 157 GB · 128K 158 GB

MiMo V2.6 Flash RL

not listed

IQ4_NL

DeepSeek V4 Flash

164 GB137.9 GB file

32K 164 GB · 128K 165 GB

MiMo V2.6 Flash RL

not listed

BF16

DeepSeek V4 Flash

582 GB~581.9 GB file

32K 583 GB · 128K 584 GB

MiMo V2.6 Flash RL

618 GB~618.0 GB file

32K 620 GB · 128K 625 GB

How to run each

DeepSeek V4 Flash

Ollama · Q4_K_M

$ollama run hf.co/teamblobfish/DeepSeek-V4-Flash-GGUF:Q4_K_M

All ways to run DeepSeek V4 Flash →

MiMo V2.6 Flash RL

Ollama · Q4_K_M

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

All ways to run MiMo V2.6 Flash RL →

Specifications

Specifications of DeepSeek V4 Flash and MiMo V2.6 Flash RL
Spec	DeepSeek V4 Flash	MiMo V2.6 Flash RL
Publisher	DeepSeek	Xiaomi
Parameters	290.9B	309B
Active parameters	14B per token	15B per token
Architecture	DeepseekV4ForCausalLM	MiMoV2ForCausalLM
Context	1M tokens	1M tokens
Modalities	Chat	Chat, Function-calling
License	MIT	MIT
Released	Apr 2026	Sep 2026

Frequently Asked Questions

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

MiMo V2.6 Flash RL leads llmrun Score 131.9 to 109.3; neither fits 24 GB. Choose DeepSeek V4 Flash for fits a Mac 128 GB; choose MiMo V2.6 Flash RL for higher llmrun Score and stronger at coding.

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

At Q4_K_M, DeepSeek V4 Flash requires 174.9 GB while MiMo V2.6 Flash RL needs 185.8 GB, making DeepSeek V4 Flash the easier model to run on your local setup.

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

DeepSeek V4 Flash does not fit (smallest quant needs 80.5 GB); MiMo V2.6 Flash RL does not fit (smallest quant needs 93.8 GB).

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

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