DeepSeek V4 Flash 0731 vs MiMo V2.6 Flash RL
MiMo V2.6 Flash RL leads llmrun Score 131.9 to 127.6 (ranges overlap); neither fits 24 GB.
Model A · DeepSeek
DeepSeek V4 Flash 0731304.2B · 27.4B active · 1M context · MIT · Jul 2026
Model B · Xiaomi
MiMo V2.6 Flash RL309B · 15B active · 1M context · MIT · Sep 2026
Choose MiMo V2.6 Flash RL if you want…
Higher llmrun Score
131.9 vs 127.6, ranges overlap
Also does function-calling
DeepSeek V4 Flash 0731 doesn't list it
DeepSeek V4 Flash 0731: no clear edge over MiMo V2.6 Flash RL in the data we have.
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 Flash 0731
Doesn't fit
smallest quant needs 84.1 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 0731
Doesn't fit
smallest quant needs 84.1 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 0731
Doesn't fit
smallest quant needs 84.1 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 0731
Doesn't fit
smallest quant needs 84.1 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 0731
Doesn't fit
smallest quant needs 84.1 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 0731
Doesn't fit
smallest quant needs 84.1 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 0731
Doesn't fit
smallest quant needs 84.1 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 0731
Doesn't fit
smallest quant needs 84.1 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 0731
Q2_K_S · ~27 tok/s
122.2 GB · up to 128K
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).
Overall
DeepSeek V4 Flash 0731
MiMo V2.6 Flash RL
Coding
DeepSeek V4 Flash 0731
MiMo V2.6 Flash RL
Math
DeepSeek V4 Flash 0731
MiMo V2.6 Flash RL
no data
Science
DeepSeek V4 Flash 0731
MiMo V2.6 Flash RL
Reasoning
DeepSeek V4 Flash 0731
MiMo V2.6 Flash RL
no data
DeepSeek V4 Flash 0731 · #7 of 100 open models · #2 of 78 that fit ≤192 GB
MiMo V2.6 Flash RL · #3 of 100 open models · #1 of 78 that fit ≤192 GB
Benchmarks
4 shared boards: DeepSeek V4 Flash 0731 leads 2, MiMo V2.6 Flash RL leads 2 · Benchmarks imported Oct 2026
DeepSeek V4 Flash 0731
49.9%#13/66 open
Lab-reportedEpoch AI · Jul 2026
MiMo V2.6 Flash RL
51.3%#7/66 open
Lab-reportedEpoch AI · Sep 2026
DeepSeek V4 Flash 0731
1306.1#4/43 open
Lab-reportedEpoch AI · Jul 2026
MiMo V2.6 Flash RL
1244.2#5/43 open
Lab-reportedEpoch AI · Sep 2026
DeepSeek V4 Flash 0731
16.6%#6/66 open
Lab-reportedEpoch AI · Jul 2026
MiMo V2.6 Flash RL
12.0%#10/66 open
Lab-reportedEpoch AI · Sep 2026
DeepSeek V4 Flash 0731
56.0%#5/26 open
Lab-reportedEpoch AI · Jul 2026
MiMo V2.6 Flash RL
63.0%#4/26 open
Lab-reportedEpoch AI · Sep 2026
19 more boards (other shared and single-model boards)
Only DeepSeek V4 Flash 0731 (17)
- GPQA Diamond91.0%
- LiveBench Coding75.0
- LiveBench Reasoning86.6
- AIME 2024/202594.4%
- FrontierMath57.5%
- LiveBench Math86.8
- ARC-AGI-261.4%
- ARC-AGI89.0%
- SimpleQA33.6%
- SimpleBench61.1%
- FrontierMath Tier 424.4%
- WeirdML63.0%
- FrontierCode18.8%
- Chess Puzzles32.0%
- DTBench90.9%
- LMCA41.7%
- Mystery Game Puzzles34.0%
Only MiMo V2.6 Flash RL (2)
- LMArena Text1450.9
- LMArena WebDev1634.3
VRAM by quantization
Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.
Q2_K
DeepSeek V4 Flash 0731
130 GB117.3 GB file
32K 130 GB · 128K 131 GB
MiMo V2.6 Flash RL
132 GB126.4 GB file
32K 133 GB · 128K 138 GB
Q3_K_M
DeepSeek V4 Flash 0731
149 GB128.1 GB file
32K 149 GB · 128K 150 GB
MiMo V2.6 Flash RL
151 GB~150.6 GB file
32K 153 GB · 128K 157 GB
Q4_0
DeepSeek V4 Flash 0731
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 0731
183 GB~182.5 GB file
32K 183 GB · 128K 184 GB
MiMo V2.6 Flash RL
186 GB~185.4 GB file
32K 187 GB · 128K 192 GB
Q5_K_M
DeepSeek V4 Flash 0731
217 GB~216.7 GB file
32K 217 GB · 128K 218 GB
MiMo V2.6 Flash RL
221 GB~220.2 GB file
32K 222 GB · 128K 227 GB
Q6_K
DeepSeek V4 Flash 0731
251 GB~250.9 GB file
32K 252 GB · 128K 253 GB
MiMo V2.6 Flash RL
255 GB~254.9 GB file
32K 257 GB · 128K 262 GB
Q8_0
DeepSeek V4 Flash 0731
305 GB~304.2 GB file
32K 305 GB · 128K 306 GB
MiMo V2.6 Flash RL
309 GB~309.0 GB file
32K 311 GB · 128K 316 GB
12 more quants
IQ2_XXS
DeepSeek V4 Flash 0731
84.0 GB90.9 GB file
32K 84.3 GB · 128K 85.4 GB
MiMo V2.6 Flash RL
not listed
IQ2_XS
DeepSeek V4 Flash 0731
91.6 GB88.1 GB file
32K 91.9 GB · 128K 93.0 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 0731
95.4 GB93.4 GB file
32K 95.7 GB · 128K 96.8 GB
MiMo V2.6 Flash RL
not listed
IQ2_M
DeepSeek V4 Flash 0731
103 GB90.9 GB file
32K 103 GB · 128K 104 GB
MiMo V2.6 Flash RL
105 GB107.8 GB file
32K 106 GB · 128K 111 GB
IQ3_XXS
DeepSeek V4 Flash 0731
118 GB104.2 GB file
32K 119 GB · 128K 120 GB
MiMo V2.6 Flash RL
not listed
Q2_K_S
DeepSeek V4 Flash 0731
122 GB98.6 GB file
32K 122 GB · 128K 123 GB
MiMo V2.6 Flash RL
not listed
IQ3_XS
DeepSeek V4 Flash 0731
126 GB118.2 GB file
32K 126 GB · 128K 127 GB
MiMo V2.6 Flash RL
not listed
IQ3_S
DeepSeek V4 Flash 0731
130 GB116.1 GB file
32K 130 GB · 128K 131 GB
MiMo V2.6 Flash RL
not listed
IQ3_M
DeepSeek V4 Flash 0731
137 GB135.8 GB file
32K 138 GB · 128K 139 GB
MiMo V2.6 Flash RL
not listed
IQ4_XS
DeepSeek V4 Flash 0731
164 GB136.7 GB file
32K 164 GB · 128K 165 GB
MiMo V2.6 Flash RL
not listed
IQ4_NL
DeepSeek V4 Flash 0731
171 GB136.7 GB file
32K 172 GB · 128K 173 GB
MiMo V2.6 Flash RL
not listed
BF16
DeepSeek V4 Flash 0731
609 GB~608.4 GB file
32K 609 GB · 128K 610 GB
MiMo V2.6 Flash RL
618 GB~618.0 GB file
32K 620 GB · 128K 625 GB
DeepSeek V4 Flash 0731
Ollama · Q4_K_M
ollama run hf.co/unsloth/DeepSeek-V4-Flash-0731-GGUFMiMo V2.6 Flash RL
Ollama · Q4_K_M
ollama run hf.co/ggml-org/MiMo-V2.6-Flash-RL-GGUF| Spec | DeepSeek V4 Flash 0731 | MiMo V2.6 Flash RL |
|---|---|---|
| Publisher | DeepSeek | Xiaomi |
| Parameters | 304.2B | 309B |
| Active parameters | 27B per token | 15B per token |
| Architecture | DeepseekV4ForCausalLM | MiMoV2ForCausalLM |
| Context | 1M tokens | 1M tokens |
| Modalities | Chat | Chat, Function-calling |
| License | MIT | MIT |
| Released | Jul 2026 | Sep 2026 |
Frequently Asked Questions
Which is better, DeepSeek V4 Flash 0731 or MiMo V2.6 Flash RL?
MiMo V2.6 Flash RL leads llmrun Score 131.9 to 127.6 (ranges overlap); neither fits 24 GB. Choose MiMo V2.6 Flash RL for higher llmrun Score and also does function-calling.
Which needs less VRAM, DeepSeek V4 Flash 0731 or MiMo V2.6 Flash RL?
At Q4_K_M, DeepSeek V4 Flash 0731 requires 182.8 GB while MiMo V2.6 Flash RL needs 185.8 GB, making DeepSeek V4 Flash 0731 the easier model to run on your local setup.
Can I run DeepSeek V4 Flash 0731 or MiMo V2.6 Flash RL on a 16 GB GPU?
DeepSeek V4 Flash 0731 does not fit (smallest quant needs 84.1 GB); MiMo V2.6 Flash RL does not fit (smallest quant needs 93.8 GB).
Which has a longer context window, DeepSeek V4 Flash 0731 or MiMo V2.6 Flash RL?
DeepSeek V4 Flash 0731 supports 1,048,576 tokens and MiMo V2.6 Flash RL supports 1,048,576 tokens.