MiMo V2.5 vs MiMo V2.6 Flash RL
MiMo V2.6 Flash RL leads llmrun Score 131.9 to 108.3; neither fits 24 GB.
Run MiMo V2.6 Flash RL in the cloud →
Model A · Xiaomi
MiMo V2.5310.8B · 17.4B active · 1M context · MIT · Apr 2026
Model B · Xiaomi
MiMo V2.6 Flash RL309B · 15B active · 1M context · MIT · Sep 2026
Choose MiMo V2.5 if you want…
Fits a Mac 128 GB
IQ3_XXS · 121.5 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 108.3
Stronger at coding
123.6 vs 103.2
Stronger at science
121.6 vs 106.8
Ahead on the benchmarks
4 of 4 shared boards
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%.
8 GB
RTX 4060 · 8 GB tier
MiMo V2.5
Doesn't fit
smallest quant needs 86.6 GB
MiMo V2.6 Flash RL
Doesn't fit
smallest quant needs 93.8 GB
12 GB
RTX 3060 12GB · 12 GB tier
MiMo V2.5
Doesn't fit
smallest quant needs 86.6 GB
MiMo V2.6 Flash RL
Doesn't fit
smallest quant needs 93.8 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
MiMo V2.5
Doesn't fit
smallest quant needs 86.6 GB
MiMo V2.6 Flash RL
Doesn't fit
smallest quant needs 93.8 GB
24 GBreference
RTX 4090 · 24 GB tier
MiMo V2.5
Doesn't fit
smallest quant needs 86.6 GB
MiMo V2.6 Flash RL
Doesn't fit
smallest quant needs 93.8 GB
32 GB
RTX 5090 · 32 GB tier
MiMo V2.5
Doesn't fit
smallest quant needs 86.6 GB
MiMo V2.6 Flash RL
Doesn't fit
smallest quant needs 93.8 GB
48 GB
RTX A6000 · 48 GB tier
MiMo V2.5
Doesn't fit
smallest quant needs 86.6 GB
MiMo V2.6 Flash RL
Doesn't fit
smallest quant needs 93.8 GB
Mac 32 GB
Mac Mini M4 · Macs
MiMo V2.5
Doesn't fit
smallest quant needs 86.6 GB
MiMo V2.6 Flash RL
Doesn't fit
smallest quant needs 93.8 GB
Mac 64 GB
Mac Studio M4 Max · Macs
MiMo V2.5
Doesn't fit
smallest quant needs 86.6 GB
MiMo V2.6 Flash RL
Doesn't fit
smallest quant needs 93.8 GB
Mac 128 GB
Mac Studio M4 Max · Macs
MiMo V2.5
IQ3_XXS · ~37 tok/s
121.5 GB · up to 64Kbetter 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).
Overall
MiMo V2.5
MiMo V2.6 Flash RL
Coding
MiMo V2.5
MiMo V2.6 Flash RL
Science
MiMo V2.5
MiMo V2.6 Flash RL
MiMo V2.5 · #38 of 106 open models · #18 of 82 that fit ≤192 GB
MiMo V2.6 Flash RL · #5 of 106 open models · #1 of 82 that fit ≤192 GB
Benchmarks
4 shared boards: MiMo V2.5 leads 0, MiMo V2.6 Flash RL leads 4 · Benchmarks imported Nov 2026
MiMo V2.5
43.1%#31/72 open
Lab-reportedEpoch AI
MiMo V2.6 Flash RL
51.3%#12/72 open
Lab-reportedEpoch AI · Sep 2026
MiMo V2.5
514.0#36/48 open
Lab-reportedEpoch AI
MiMo V2.6 Flash RL
1244.2#8/48 open
Lab-reportedEpoch AI · Sep 2026
MiMo V2.5
3.7%#26/84 open
Lab-reportedEpoch AI
MiMo V2.6 Flash RL
12.0%#14/84 open
Lab-reportedEpoch AI · Sep 2026
MiMo V2.5
16.0%#20/31 open
Lab-reportedEpoch AI
MiMo V2.6 Flash RL
63.0%#5/31 open
Lab-reportedEpoch AI · Sep 2026
2 more boards (other shared and single-model boards)
MiMo V2.5
1433.9#25/188 open
ArenaLMArena · Oct 2026
MiMo V2.6 Flash RL
1447.6#16/188 open
ArenaLMArena · Oct 2026
MiMo V2.5
1438.3#23/55 open
ArenaLMArena · Oct 2026
MiMo V2.6 Flash RL
1637.2#3/55 open
ArenaLMArena · Oct 2026
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
MiMo V2.5
132 GB108.9 GB file
32K 134 GB · 128K 139 GB
MiMo V2.6 Flash RL
132 GB126.4 GB file
32K 133 GB · 128K 138 GB
Q3_K_S
MiMo V2.5
136 GB135.1 GB file
32K 138 GB · 128K 143 GB
MiMo V2.6 Flash RL
not listed
Q3_K_M
MiMo V2.5
152 GB140.0 GB file
32K 153 GB · 128K 158 GB
MiMo V2.6 Flash RL
151 GB~150.6 GB file
32K 153 GB · 128K 157 GB
Q4_0
MiMo V2.5
156 GB175.8 GB file
32K 157 GB · 128K 162 GB
MiMo V2.6 Flash RL
155 GB~154.5 GB file
32K 156 GB · 128K 161 GB
Q4_K_M
MiMo V2.5
187 GB190.9 GB file
32K 188 GB · 128K 193 GB
MiMo V2.6 Flash RL
186 GB~185.4 GB file
32K 187 GB · 128K 192 GB
Q5_K_M
MiMo V2.5
222 GB230.2 GB file
32K 223 GB · 128K 228 GB
MiMo V2.6 Flash RL
221 GB~220.2 GB file
32K 222 GB · 128K 227 GB
Q6_K
MiMo V2.5
257 GB257.0 GB file
32K 258 GB · 128K 263 GB
MiMo V2.6 Flash RL
255 GB~254.9 GB file
32K 257 GB · 128K 262 GB
Q8_0
MiMo V2.5
311 GB329.3 GB file
32K 313 GB · 128K 318 GB
MiMo V2.6 Flash RL
309 GB~309.0 GB file
32K 311 GB · 128K 316 GB
16 more quants
IQ2_XXS
MiMo V2.5
85.9 GB96.5 GB file
32K 87.4 GB · 128K 92.2 GB
MiMo V2.6 Flash RL
not listed
IQ2_XS
MiMo V2.5
93.6 GB93.1 GB file
32K 95.1 GB · 128K 100 GB
MiMo V2.6 Flash RL
93.1 GB98.7 GB file
32K 94.6 GB · 128K 99.4 GB
IQ2_S
MiMo V2.5
97.5 GB94.7 GB file
32K 99.0 GB · 128K 104 GB
MiMo V2.6 Flash RL
not listed
IQ2_M
MiMo V2.5
105 GB96.6 GB file
32K 107 GB · 128K 112 GB
MiMo V2.6 Flash RL
105 GB107.8 GB file
32K 106 GB · 128K 111 GB
IQ3_XXS
MiMo V2.5
121 GB125.9 GB file
32K 122 GB · 128K 127 GB
MiMo V2.6 Flash RL
not listed
IQ3_XS
MiMo V2.5
129 GB142.2 GB file
32K 130 GB · 128K 135 GB
MiMo V2.6 Flash RL
not listed
IQ3_S
MiMo V2.5
132 GB114.9 GB file
32K 134 GB · 128K 139 GB
MiMo V2.6 Flash RL
132 GB146.8 GB file
32K 133 GB · 128K 138 GB
IQ3_M
MiMo V2.5
140 GB148.3 GB file
32K 142 GB · 128K 147 GB
MiMo V2.6 Flash RL
139 GB148.6 GB file
32K 141 GB · 128K 146 GB
Q3_K_L
MiMo V2.5
160 GB147.9 GB file
32K 161 GB · 128K 166 GB
MiMo V2.6 Flash RL
not listed
IQ4_XS
MiMo V2.5
167 GB149.4 GB file
32K 169 GB · 128K 174 GB
MiMo V2.6 Flash RL
not listed
IQ4_NL
MiMo V2.5
175 GB152.6 GB file
32K 177 GB · 128K 182 GB
MiMo V2.6 Flash RL
not listed
Q4_1
MiMo V2.5
175 GB194.3 GB file
32K 177 GB · 128K 182 GB
MiMo V2.6 Flash RL
not listed
Q4_K_S
MiMo V2.5
175 GB178.8 GB file
32K 177 GB · 128K 182 GB
MiMo V2.6 Flash RL
not listed
Q4_K_L
MiMo V2.5
191 GB189.2 GB file
32K 192 GB · 128K 197 GB
MiMo V2.6 Flash RL
not listed
Q5_K_S
MiMo V2.5
214 GB216.3 GB file
32K 216 GB · 128K 220 GB
MiMo V2.6 Flash RL
not listed
BF16
MiMo V2.5
622 GB619.6 GB file
32K 623 GB · 128K 628 GB
MiMo V2.6 Flash RL
618 GB~618.0 GB file
32K 620 GB · 128K 625 GB
MiMo V2.5
Ollama · Q4_K_M
ollama run hf.co/unsloth/MiMo-V2.5-GGUF:Q4_K_MMiMo V2.6 Flash RL
Ollama · Q4_K_M
ollama run hf.co/vultr/MiMo-V2.6-Flash-RL-GGUF| Spec | MiMo V2.5 | MiMo V2.6 Flash RL |
|---|---|---|
| Publisher | Xiaomi | Xiaomi |
| Parameters | 310.8B | 309B |
| Active parameters | 17B per token | 15B per token |
| Architecture | MiMoV2ForCausalLM | MiMoV2ForCausalLM |
| Context | 1M tokens | 1M tokens |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | MIT | MIT |
| Released | Apr 2026 | Sep 2026 |
Frequently Asked Questions
Which is better, MiMo V2.5 or MiMo V2.6 Flash RL?
MiMo V2.6 Flash RL leads llmrun Score 131.9 to 108.3; neither fits 24 GB. Choose MiMo V2.5 for fits a Mac 128 GB; choose MiMo V2.6 Flash RL for higher llmrun Score and stronger at coding.
Which needs less VRAM, MiMo V2.5 or MiMo V2.6 Flash RL?
At Q4_K_M, MiMo V2.5 requires 186.9 GB while MiMo V2.6 Flash RL needs 185.8 GB, making MiMo V2.6 Flash RL the easier model to run on your local setup.
Can I run MiMo V2.5 or MiMo V2.6 Flash RL on a 16 GB GPU?
MiMo V2.5 does not fit (smallest quant needs 86.6 GB); MiMo V2.6 Flash RL does not fit (smallest quant needs 93.8 GB).
Which has a longer context window, MiMo V2.5 or MiMo V2.6 Flash RL?
MiMo V2.5 supports 1,048,576 tokens and MiMo V2.6 Flash RL supports 1,048,576 tokens.