Qwen3 235B A22B Thinking 2507 vs MiMo V2.5

Qwen3 235B A22B Thinking 2507 and MiMo V2.5 match in llmrun Score, with values of 108.1 versus 108.3; neither fits 24 GB.

Model A · Alibaba

Qwen3 235B A22B Thinking 2507

108.1llmrun Score

235.1B · 22.2B active · 256K context · Apache 2.0 · Jul 2025

ChatFunctions

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 Qwen3 235B A22B Thinking 2507 if you want…

Lighter on memory
141.6 vs 186.9 GB at Q4_K_M

Choose MiMo V2.5 if you want…

Ahead on the benchmarks
3 of 3 shared boards
Longer context window
1M vs 256K tokens
Newer release
Apr 2026 vs Jul 2025

On your hardware

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

MemoryQwen3 235B A22B Thinking 2507MiMo V2.5

8 GB

RTX 4060 · 8 GB tier

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

24 GBreference

RTX 4090 · 24 GB tier

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

32 GB

RTX 5090 · 32 GB tier

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

48 GB

RTX A6000 · 48 GB tier

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

Mac 32 GB

Mac Mini M4 · Macs

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

MiMo V2.5

Doesn't fit

smallest quant needs 86.6 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3 235B A22B Thinking 2507

Q3_K_L · ~21 tok/s

122.4 GB · up to 32K

MiMo V2.5

IQ3_XXS · ~37 tok/s

121.5 GB · up to 64K

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

Qwen3 235B A22B Thinking 2507 MiMo V2.5

Overall

Qwen3 235B A22B Thinking 2507

108.1105–112

MiMo V2.5

108.399–118

Coding

Qwen3 235B A22B Thinking 2507

102.693–113

MiMo V2.5

103.390–116

Science

Qwen3 235B A22B Thinking 2507

107.799–116

MiMo V2.5

106.987–127

Reasoning

Qwen3 235B A22B Thinking 2507

105.998–113

MiMo V2.5

no data

Qwen3 235B A22B Thinking 2507 · #31 of 92 open models · #15 of 71 that fit ≤192 GB

MiMo V2.5 · #30 of 92 open models · #13 of 71 that fit ≤192 GB

Benchmarks

3 shared boards: Qwen3 235B A22B Thinking 2507 leads 0, MiMo V2.5 leads 3 · Benchmarks imported Oct 2026

BoardQwen3 235B A22B Thinking 2507MiMo V2.5

LMArena Text

Qwen3 235B A22B Thinking 2507

1400.0#48/186 open

ArenaLMArena · Oct 2026

MiMo V2.5

1433.7#24/186 open

ArenaLMArena · Oct 2026

SciCode

Qwen3 235B A22B Thinking 2507

42.4%#26/65 open

Lab-reportedEpoch AI · Jul 2025

MiMo V2.5

43.1%#24/65 open

Lab-reportedEpoch AI

CritPt

Qwen3 235B A22B Thinking 2507

0.0%#62/65 open

Lab-reportedEpoch AI · Jul 2025

MiMo V2.5

3.7%#21/65 open

Lab-reportedEpoch AI

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

Only Qwen3 235B A22B Thinking 2507 (11)

Only MiMo V2.5 (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.

QuantQwen3 235B A22B Thinking 2507MiMo V2.5

Q2_K

Qwen3 235B A22B Thinking 2507

100 GB85.7 GB file

32K 103 GB · 128K 113 GB

MiMo V2.5

132 GB108.9 GB file

32K 134 GB · 128K 139 GB

Q3_K_S

Qwen3 235B A22B Thinking 2507

103 GB101.4 GB file

32K 106 GB · 128K 116 GB

MiMo V2.5

136 GB135.1 GB file

32K 138 GB · 128K 143 GB

Q3_K_M

Qwen3 235B A22B Thinking 2507

115 GB112.4 GB file

32K 118 GB · 128K 128 GB

MiMo V2.5

152 GB140.0 GB file

32K 153 GB · 128K 158 GB

Q4_0

Qwen3 235B A22B Thinking 2507

118 GB133.1 GB file

32K 121 GB · 128K 130 GB

MiMo V2.5

156 GB175.8 GB file

32K 157 GB · 128K 162 GB

Q4_K_M

Qwen3 235B A22B Thinking 2507

142 GB142.2 GB file

32K 145 GB · 128K 154 GB

MiMo V2.5

187 GB190.9 GB file

32K 188 GB · 128K 193 GB

Q5_K_M

Qwen3 235B A22B Thinking 2507

168 GB166.8 GB file

32K 171 GB · 128K 180 GB

MiMo V2.5

222 GB230.2 GB file

32K 223 GB · 128K 228 GB

Q6_K

Qwen3 235B A22B Thinking 2507

194 GB193.0 GB file

32K 197 GB · 128K 207 GB

MiMo V2.5

257 GB257.0 GB file

32K 258 GB · 128K 263 GB

Q8_0

Qwen3 235B A22B Thinking 2507

236 GB249.9 GB file

32K 239 GB · 128K 248 GB

MiMo V2.5

311 GB329.3 GB file

32K 313 GB · 128K 318 GB

16 more quants

IQ2_XXS

Qwen3 235B A22B Thinking 2507

not listed

MiMo V2.5

85.9 GB96.5 GB file

32K 87.4 GB · 128K 92.2 GB

IQ2_XS

Qwen3 235B A22B Thinking 2507

71.0 GB65.6 GB file

32K 74.0 GB · 128K 83.5 GB

MiMo V2.5

93.6 GB93.1 GB file

32K 95.1 GB · 128K 100 GB

IQ2_S

Qwen3 235B A22B Thinking 2507

74.0 GB66.1 GB file

32K 76.9 GB · 128K 86.4 GB

MiMo V2.5

97.5 GB94.7 GB file

32K 99.0 GB · 128K 104 GB

IQ2_M

Qwen3 235B A22B Thinking 2507

79.8 GB78.6 GB file

32K 82.8 GB · 128K 92.3 GB

MiMo V2.5

105 GB96.6 GB file

32K 107 GB · 128K 112 GB

IQ3_XXS

Qwen3 235B A22B Thinking 2507

91.6 GB93.1 GB file

32K 94.6 GB · 128K 104 GB

MiMo V2.5

121 GB125.9 GB file

32K 122 GB · 128K 127 GB

IQ3_XS

Qwen3 235B A22B Thinking 2507

97.5 GB96.9 GB file

32K 100 GB · 128K 110 GB

MiMo V2.5

129 GB142.2 GB file

32K 130 GB · 128K 135 GB

IQ3_S

Qwen3 235B A22B Thinking 2507

not listed

MiMo V2.5

132 GB114.9 GB file

32K 134 GB · 128K 139 GB

IQ3_M

Qwen3 235B A22B Thinking 2507

106 GB107.3 GB file

32K 109 GB · 128K 119 GB

MiMo V2.5

140 GB148.3 GB file

32K 142 GB · 128K 147 GB

Q3_K_L

Qwen3 235B A22B Thinking 2507

121 GB111.2 GB file

32K 124 GB · 128K 133 GB

MiMo V2.5

160 GB147.9 GB file

32K 161 GB · 128K 166 GB

IQ4_XS

Qwen3 235B A22B Thinking 2507

127 GB125.5 GB file

32K 130 GB · 128K 139 GB

MiMo V2.5

167 GB149.4 GB file

32K 169 GB · 128K 174 GB

IQ4_NL

Qwen3 235B A22B Thinking 2507

133 GB133.1 GB file

32K 136 GB · 128K 145 GB

MiMo V2.5

175 GB152.6 GB file

32K 177 GB · 128K 182 GB

Q4_1

Qwen3 235B A22B Thinking 2507

133 GB147.2 GB file

32K 136 GB · 128K 145 GB

MiMo V2.5

175 GB194.3 GB file

32K 177 GB · 128K 182 GB

Q4_K_S

Qwen3 235B A22B Thinking 2507

133 GB133.7 GB file

32K 136 GB · 128K 145 GB

MiMo V2.5

175 GB178.8 GB file

32K 177 GB · 128K 182 GB

Q4_K_L

Qwen3 235B A22B Thinking 2507

not listed

MiMo V2.5

191 GB189.2 GB file

32K 192 GB · 128K 197 GB

Q5_K_S

Qwen3 235B A22B Thinking 2507

162 GB161.9 GB file

32K 165 GB · 128K 175 GB

MiMo V2.5

214 GB216.3 GB file

32K 216 GB · 128K 220 GB

BF16

Qwen3 235B A22B Thinking 2507

471 GB470.3 GB file

32K 474 GB · 128K 483 GB

MiMo V2.5

622 GB619.6 GB file

32K 623 GB · 128K 628 GB

How to run each

Qwen3 235B A22B Thinking 2507

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF:Q4_K_M

All ways to run Qwen3 235B A22B Thinking 2507 →

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 Qwen3 235B A22B Thinking 2507 and MiMo V2.5
Spec	Qwen3 235B A22B Thinking 2507	MiMo V2.5
Publisher	Alibaba	Xiaomi
Parameters	235.1B	310.8B
Active parameters	22B per token	17B per token
Architecture	Qwen3MoeForCausalLM	MiMoV2ForCausalLM
Context	256K tokens	1M tokens
Modalities	Chat, Function-calling	Chat, Function-calling
License	Apache 2.0	MIT
Released	Jul 2025	Apr 2026

Frequently Asked Questions

Which is better, Qwen3 235B A22B Thinking 2507 or MiMo V2.5?

Qwen3 235B A22B Thinking 2507 and MiMo V2.5 match in llmrun Score, with values of 108.1 versus 108.3; neither fits 24 GB. Choose Qwen3 235B A22B Thinking 2507 for lighter on memory; choose MiMo V2.5 for ahead on the benchmarks and longer context window.

Which needs less VRAM, Qwen3 235B A22B Thinking 2507 or MiMo V2.5?

At Q4_K_M, Qwen3 235B A22B Thinking 2507 requires 141.6 GB while MiMo V2.5 needs 186.9 GB, making Qwen3 235B A22B Thinking 2507 the easier model to run on your local setup.

Can I run Qwen3 235B A22B Thinking 2507 or MiMo V2.5 on a 16 GB GPU?

Qwen3 235B A22B Thinking 2507 does not fit (smallest quant needs 72.4 GB); MiMo V2.5 does not fit (smallest quant needs 86.6 GB).

Which has a longer context window, Qwen3 235B A22B Thinking 2507 or MiMo V2.5?

Qwen3 235B A22B Thinking 2507 supports 262,144 tokens and MiMo V2.5 supports 1,048,576 tokens.