DeepSeek V4 Flash 0731 vs MiMo V2.5

DeepSeek V4 Flash 0731 leads llmrun Score 127.6 to 108.3; neither fits 24 GB.

Run DeepSeek V4 Flash 0731 in the cloud →

Model A · DeepSeek

DeepSeek V4 Flash 0731

127.6llmrun Score

304.2B · 27.4B active · 1M context · MIT · Jul 2026

Chat

Model B · Xiaomi

MiMo V2.5

108.3llmrun Score

310.8B · 17.4B active · 1M context · MIT · Apr 2026

ChatFunctions

Which should you choose?

Choose DeepSeek V4 Flash 0731 if you want…

Higher llmrun Score
127.6 vs 108.3
Stronger at coding
120.7 vs 103.2
Stronger at science
124.1 vs 106.8
Ahead on the benchmarks
4 of 4 shared boards
Newer release
Jul 2026 vs Apr 2026

Choose MiMo V2.5 if you want…

Fits a Mac 128 GB
IQ3_XXS · 121.5 GB; DeepSeek V4 Flash 0731 needs 84.1 GB at its smallest quant
Also does function-calling
DeepSeek V4 Flash 0731 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 Flash 0731MiMo V2.5

8 GB

RTX 4060 · 8 GB tier

DeepSeek V4 Flash 0731

Doesn't fit

smallest quant needs 84.1 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

12 GB

RTX 3060 12GB · 12 GB tier

DeepSeek V4 Flash 0731

Doesn't fit

smallest quant needs 84.1 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

DeepSeek V4 Flash 0731

Doesn't fit

smallest quant needs 84.1 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

24 GBreference

RTX 4090 · 24 GB tier

DeepSeek V4 Flash 0731

Doesn't fit

smallest quant needs 84.1 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

32 GB

RTX 5090 · 32 GB tier

DeepSeek V4 Flash 0731

Doesn't fit

smallest quant needs 84.1 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

48 GB

RTX A6000 · 48 GB tier

DeepSeek V4 Flash 0731

Doesn't fit

smallest quant needs 84.1 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

Mac 32 GB

Mac Mini M4 · Macs

DeepSeek V4 Flash 0731

Doesn't fit

smallest quant needs 84.1 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

Mac 64 GB

Mac Studio M4 Max · Macs

DeepSeek V4 Flash 0731

Doesn't fit

smallest quant needs 84.1 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

Mac 128 GB

Mac Studio M4 Max · Macs

DeepSeek V4 Flash 0731

Q2_K_S · ~27 tok/s

122.2 GB · up to 128K

MiMo V2.5

IQ3_XXS · ~37 tok/s

121.5 GB · up to 64Kbetter quant

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 0731 MiMo V2.5

Overall

DeepSeek V4 Flash 0731

127.6126–129

MiMo V2.5

108.398–118

Coding

DeepSeek V4 Flash 0731

120.7114–128

MiMo V2.5

103.290–117

Math

DeepSeek V4 Flash 0731

128.1126–131

MiMo V2.5

no data

Science

DeepSeek V4 Flash 0731

124.1112–136

MiMo V2.5

106.886–127

Reasoning

DeepSeek V4 Flash 0731

128.7126–132

MiMo V2.5

no data

DeepSeek V4 Flash 0731 · #10 of 106 open models · #3 of 82 that fit ≤192 GB

MiMo V2.5 · #38 of 106 open models · #18 of 82 that fit ≤192 GB

Benchmarks

4 shared boards: DeepSeek V4 Flash 0731 leads 4, MiMo V2.5 leads 0 · Benchmarks imported Nov 2026

BoardDeepSeek V4 Flash 0731MiMo V2.5

SciCode

DeepSeek V4 Flash 0731

49.9%#18/72 open

Lab-reportedEpoch AI · Jul 2026

MiMo V2.5

43.1%#31/72 open

Lab-reportedEpoch AI

ALE-Bench

DeepSeek V4 Flash 0731

1306.1#7/48 open

Lab-reportedEpoch AI · Jul 2026

MiMo V2.5

514.0#36/48 open

Lab-reportedEpoch AI

CritPt

DeepSeek V4 Flash 0731

16.6%#9/84 open

Lab-reportedEpoch AI · Jul 2026

MiMo V2.5

3.7%#26/84 open

Lab-reportedEpoch AI

ProofBench

DeepSeek V4 Flash 0731

56.0%#6/31 open

Lab-reportedEpoch AI · Jul 2026

MiMo V2.5

16.0%#20/31 open

Lab-reportedEpoch AI

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

Only DeepSeek V4 Flash 0731 (17)

Only MiMo V2.5 (2)

LMArena Text1433.9
LMArena WebDev1438.3

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 Flash 0731MiMo V2.5

Q2_K

DeepSeek V4 Flash 0731

130 GB117.3 GB file

32K 130 GB · 128K 131 GB

MiMo V2.5

132 GB108.9 GB file

32K 134 GB · 128K 139 GB

Q3_K_S

DeepSeek V4 Flash 0731

not listed

MiMo V2.5

136 GB135.1 GB file

32K 138 GB · 128K 143 GB

Q3_K_M

DeepSeek V4 Flash 0731

149 GB128.1 GB file

32K 149 GB · 128K 150 GB

MiMo V2.5

152 GB140.0 GB file

32K 153 GB · 128K 158 GB

Q4_0

DeepSeek V4 Flash 0731

not listed

MiMo V2.5

156 GB175.8 GB file

32K 157 GB · 128K 162 GB

Q4_K_M

DeepSeek V4 Flash 0731

183 GB~182.5 GB file

32K 183 GB · 128K 184 GB

MiMo V2.5

187 GB190.9 GB file

32K 188 GB · 128K 193 GB

Q5_K_M

DeepSeek V4 Flash 0731

217 GB~216.7 GB file

32K 217 GB · 128K 218 GB

MiMo V2.5

222 GB230.2 GB file

32K 223 GB · 128K 228 GB

Q6_K

DeepSeek V4 Flash 0731

251 GB~250.9 GB file

32K 252 GB · 128K 253 GB

MiMo V2.5

257 GB257.0 GB file

32K 258 GB · 128K 263 GB

Q8_0

DeepSeek V4 Flash 0731

305 GB~304.2 GB file

32K 305 GB · 128K 306 GB

MiMo V2.5

311 GB329.3 GB file

32K 313 GB · 128K 318 GB

17 more quants

IQ2_XXS

DeepSeek V4 Flash 0731

84.0 GB90.9 GB file

32K 84.3 GB · 128K 85.4 GB

MiMo V2.5

85.9 GB96.5 GB file

32K 87.4 GB · 128K 92.2 GB

IQ2_XS

DeepSeek V4 Flash 0731

91.6 GB85.1 GB file

32K 91.9 GB · 128K 93.0 GB

MiMo V2.5

93.6 GB93.1 GB file

32K 95.1 GB · 128K 100 GB

IQ2_S

DeepSeek V4 Flash 0731

95.4 GB93.4 GB file

32K 95.7 GB · 128K 96.8 GB

MiMo V2.5

97.5 GB94.7 GB file

32K 99.0 GB · 128K 104 GB

IQ2_M

DeepSeek V4 Flash 0731

103 GB90.9 GB file

32K 103 GB · 128K 104 GB

MiMo V2.5

105 GB96.6 GB file

32K 107 GB · 128K 112 GB

IQ3_XXS

DeepSeek V4 Flash 0731

118 GB104.2 GB file

32K 119 GB · 128K 120 GB

MiMo V2.5

121 GB125.9 GB file

32K 122 GB · 128K 127 GB

Q2_K_S

DeepSeek V4 Flash 0731

122 GB98.6 GB file

32K 122 GB · 128K 123 GB

MiMo V2.5

not listed

IQ3_XS

DeepSeek V4 Flash 0731

126 GB118.2 GB file

32K 126 GB · 128K 127 GB

MiMo V2.5

129 GB142.2 GB file

32K 130 GB · 128K 135 GB

IQ3_S

DeepSeek V4 Flash 0731

130 GB116.1 GB file

32K 130 GB · 128K 131 GB

MiMo V2.5

132 GB114.9 GB file

32K 134 GB · 128K 139 GB

IQ3_M

DeepSeek V4 Flash 0731

137 GB135.8 GB file

32K 138 GB · 128K 139 GB

MiMo V2.5

140 GB148.3 GB file

32K 142 GB · 128K 147 GB

Q3_K_L

DeepSeek V4 Flash 0731

not listed

MiMo V2.5

160 GB147.9 GB file

32K 161 GB · 128K 166 GB

IQ4_XS

DeepSeek V4 Flash 0731

164 GB136.7 GB file

32K 164 GB · 128K 165 GB

MiMo V2.5

167 GB149.4 GB file

32K 169 GB · 128K 174 GB

IQ4_NL

DeepSeek V4 Flash 0731

171 GB136.7 GB file

32K 172 GB · 128K 173 GB

MiMo V2.5

175 GB152.6 GB file

32K 177 GB · 128K 182 GB

Q4_1

DeepSeek V4 Flash 0731

not listed

MiMo V2.5

175 GB194.3 GB file

32K 177 GB · 128K 182 GB

Q4_K_S

DeepSeek V4 Flash 0731

not listed

MiMo V2.5

175 GB178.8 GB file

32K 177 GB · 128K 182 GB

Q4_K_L

DeepSeek V4 Flash 0731

not listed

MiMo V2.5

191 GB189.2 GB file

32K 192 GB · 128K 197 GB

Q5_K_S

DeepSeek V4 Flash 0731

not listed

MiMo V2.5

214 GB216.3 GB file

32K 216 GB · 128K 220 GB

BF16

DeepSeek V4 Flash 0731

609 GB~608.4 GB file

32K 609 GB · 128K 610 GB

MiMo V2.5

622 GB619.6 GB file

32K 623 GB · 128K 628 GB

How to run each

DeepSeek V4 Flash 0731

Ollama · Q4_K_M

$ollama run hf.co/unsloth/DeepSeek-V4-Flash-0731-GGUF

All ways to run DeepSeek V4 Flash 0731 →

MiMo V2.5

Ollama · Q4_K_M

$ollama run hf.co/unsloth/MiMo-V2.5-GGUF:Q4_K_M

All ways to run MiMo V2.5 →

Specifications

Specifications of DeepSeek V4 Flash 0731 and MiMo V2.5
Spec	DeepSeek V4 Flash 0731	MiMo V2.5
Publisher	DeepSeek	Xiaomi
Parameters	304.2B	310.8B
Active parameters	27B per token	17B per token
Architecture	DeepseekV4ForCausalLM	MiMoV2ForCausalLM
Context	1M tokens	1M tokens
Modalities	Chat	Chat, Function-calling
License	MIT	MIT
Released	Jul 2026	Apr 2026

Frequently Asked Questions

Which is better, DeepSeek V4 Flash 0731 or MiMo V2.5?

DeepSeek V4 Flash 0731 leads llmrun Score 127.6 to 108.3; neither fits 24 GB. Choose DeepSeek V4 Flash 0731 for higher llmrun Score and stronger at coding; choose MiMo V2.5 for fits a Mac 128 GB and also does function-calling.

Which needs less VRAM, DeepSeek V4 Flash 0731 or MiMo V2.5?

At Q4_K_M, DeepSeek V4 Flash 0731 requires 182.8 GB while MiMo V2.5 needs 186.9 GB, making DeepSeek V4 Flash 0731 the easier model to run on your local setup.

Can I run DeepSeek V4 Flash 0731 or MiMo V2.5 on a 16 GB GPU?

DeepSeek V4 Flash 0731 does not fit (smallest quant needs 84.1 GB); MiMo V2.5 does not fit (smallest quant needs 86.6 GB).

Which has a longer context window, DeepSeek V4 Flash 0731 or MiMo V2.5?

DeepSeek V4 Flash 0731 supports 1,048,576 tokens and MiMo V2.5 supports 1,048,576 tokens.