MiniMax M2.7 vs Qwen3 235B A22B Thinking 2507

MiniMax M2.7 and Qwen3 235B A22B Thinking 2507 match in llmrun Score, with values of 106.8 versus 108.1; neither fits 24 GB.

Model A · MiniMax

MiniMax M2.7

106.8llmrun Score

228.7B · 11B active · 200K context · Other · Apr 2026

ChatFunctions

Model B · Alibaba

Qwen3 235B A22B Thinking 2507

108.1llmrun Score

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

ChatFunctions

Which should you choose?

Choose MiniMax M2.7 if you want…

Ahead on the benchmarks
3 of 4 shared boards
Newer release
Apr 2026 vs Jul 2025

Choose Qwen3 235B A22B Thinking 2507 if you want…

More permissive license
Apache 2.0 vs Other

On your hardware

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

MemoryMiniMax M2.7Qwen3 235B A22B Thinking 2507

8 GB

RTX 4060 · 8 GB tier

MiniMax M2.7

Doesn't fit

smallest quant needs 65.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

12 GB

RTX 3060 12GB · 12 GB tier

MiniMax M2.7

Doesn't fit

smallest quant needs 65.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

MiniMax M2.7

Doesn't fit

smallest quant needs 65.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

24 GBreference

RTX 4090 · 24 GB tier

MiniMax M2.7

Doesn't fit

smallest quant needs 65.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

32 GB

RTX 5090 · 32 GB tier

MiniMax M2.7

Doesn't fit

smallest quant needs 65.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

48 GB

RTX A6000 · 48 GB tier

MiniMax M2.7

Doesn't fit

smallest quant needs 65.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

Mac 32 GB

Mac Mini M4 · Macs

MiniMax M2.7

Doesn't fit

smallest quant needs 65.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

Mac 64 GB

Mac Studio M4 Max · Macs

MiniMax M2.7

Doesn't fit

smallest quant needs 65.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

Mac 128 GB

Mac Studio M4 Max · Macs

MiniMax M2.7

Q3_K_L · ~37 tok/s

119.6 GB · up to 32Kfaster

Qwen3 235B A22B Thinking 2507

Q3_K_L · ~21 tok/s

122.4 GB · up to 32K

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

MiniMax M2.7 Qwen3 235B A22B Thinking 2507

Overall

MiniMax M2.7

106.8101–112

Qwen3 235B A22B Thinking 2507

108.1105–112

Coding

MiniMax M2.7

102.093–111

Qwen3 235B A22B Thinking 2507

102.693–113

Science

MiniMax M2.7

109.290–129

Qwen3 235B A22B Thinking 2507

107.799–116

Reasoning

MiniMax M2.7

no data

Qwen3 235B A22B Thinking 2507

105.998–113

MiniMax M2.7 · #34 of 92 open models · #18 of 71 that fit ≤192 GB

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

Benchmarks

4 shared boards: MiniMax M2.7 leads 3, Qwen3 235B A22B Thinking 2507 leads 1 · Benchmarks imported Oct 2026

BoardMiniMax M2.7Qwen3 235B A22B Thinking 2507

LMArena Text

MiniMax M2.7

1415.0#39/186 open

ArenaLMArena · Oct 2026

Qwen3 235B A22B Thinking 2507

1400.0#48/186 open

ArenaLMArena · Oct 2026

SciCode

MiniMax M2.7

47.0%#17/65 open

Lab-reportedEpoch AI · Mar 2026

Qwen3 235B A22B Thinking 2507

42.4%#26/65 open

Lab-reportedEpoch AI · Jul 2025

WeirdML

MiniMax M2.7

37.0%#30/46 open

IndependentEpoch AI · Mar 2026

Qwen3 235B A22B Thinking 2507

41.0%#20/46 open

IndependentEpoch AI · Jul 2025

CritPt

MiniMax M2.7

0.6%#37/65 open

Lab-reportedEpoch AI · Mar 2026

Qwen3 235B A22B Thinking 2507

0.0%#62/65 open

Lab-reportedEpoch AI · Jul 2025

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

Only MiniMax M2.7 (4)

Only Qwen3 235B A22B Thinking 2507 (10)

VRAM by quantization

Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.

QuantMiniMax M2.7Qwen3 235B A22B Thinking 2507

Q2_K

MiniMax M2.7

97.8 GB80.1 GB file

32K 102 GB · 128K 114 GB

Qwen3 235B A22B Thinking 2507

100 GB85.7 GB file

32K 103 GB · 128K 113 GB

Q3_K_S

MiniMax M2.7

101 GB93.6 GB file

32K 105 GB · 128K 117 GB

Qwen3 235B A22B Thinking 2507

103 GB101.4 GB file

32K 106 GB · 128K 116 GB

Q3_K_M

MiniMax M2.7

112 GB101.2 GB file

32K 116 GB · 128K 128 GB

Qwen3 235B A22B Thinking 2507

115 GB112.4 GB file

32K 118 GB · 128K 128 GB

Q4_0

MiniMax M2.7

115 GB129.8 GB file

32K 119 GB · 128K 131 GB

Qwen3 235B A22B Thinking 2507

118 GB133.1 GB file

32K 121 GB · 128K 130 GB

Q4_K_M

MiniMax M2.7

138 GB140.2 GB file

32K 142 GB · 128K 154 GB

Qwen3 235B A22B Thinking 2507

142 GB142.2 GB file

32K 145 GB · 128K 154 GB

Q5_K_M

MiniMax M2.7

164 GB168.8 GB file

32K 167 GB · 128K 180 GB

Qwen3 235B A22B Thinking 2507

168 GB166.8 GB file

32K 171 GB · 128K 180 GB

Q6_K

MiniMax M2.7

189 GB188.1 GB file

32K 193 GB · 128K 206 GB

Qwen3 235B A22B Thinking 2507

194 GB193.0 GB file

32K 197 GB · 128K 207 GB

Q8_0

MiniMax M2.7

229 GB243.1 GB file

32K 233 GB · 128K 246 GB

Qwen3 235B A22B Thinking 2507

236 GB249.9 GB file

32K 239 GB · 128K 248 GB

19 more quants

IQ2_XXS

MiniMax M2.7

63.5 GB65.4 GB file

32K 67.4 GB · 128K 79.8 GB

Qwen3 235B A22B Thinking 2507

not listed

IQ2_XS

MiniMax M2.7

69.2 GB67.9 GB file

32K 73.1 GB · 128K 85.6 GB

Qwen3 235B A22B Thinking 2507

71.0 GB65.6 GB file

32K 74.0 GB · 128K 83.5 GB

IQ2_S

MiniMax M2.7

72.0 GB69.1 GB file

32K 75.9 GB · 128K 88.4 GB

Qwen3 235B A22B Thinking 2507

74.0 GB66.1 GB file

32K 76.9 GB · 128K 86.4 GB

IQ2_M

MiniMax M2.7

77.7 GB70.1 GB file

32K 81.6 GB · 128K 94.1 GB

Qwen3 235B A22B Thinking 2507

79.8 GB78.6 GB file

32K 82.8 GB · 128K 92.3 GB

IQ3_XXS

MiniMax M2.7

89.2 GB80.1 GB file

32K 93.1 GB · 128K 106 GB

Qwen3 235B A22B Thinking 2507

91.6 GB93.1 GB file

32K 94.6 GB · 128K 104 GB

Q2_K_S

MiniMax M2.7

92.0 GB77.6 GB file

32K 95.9 GB · 128K 108 GB

Qwen3 235B A22B Thinking 2507

not listed

IQ3_XS

MiniMax M2.7

94.9 GB104.1 GB file

32K 98.8 GB · 128K 111 GB

Qwen3 235B A22B Thinking 2507

97.5 GB96.9 GB file

32K 100 GB · 128K 110 GB

IQ3_S

MiniMax M2.7

97.8 GB83.6 GB file

32K 102 GB · 128K 114 GB

Qwen3 235B A22B Thinking 2507

not listed

IQ3_M

MiniMax M2.7

103 GB108.8 GB file

32K 107 GB · 128K 120 GB

Qwen3 235B A22B Thinking 2507

106 GB107.3 GB file

32K 109 GB · 128K 119 GB

Q3_K_L

MiniMax M2.7

118 GB108.5 GB file

32K 122 GB · 128K 134 GB

Qwen3 235B A22B Thinking 2507

121 GB111.2 GB file

32K 124 GB · 128K 133 GB

IQ4_XS

MiniMax M2.7

123 GB108.4 GB file

32K 127 GB · 128K 140 GB

Qwen3 235B A22B Thinking 2507

127 GB125.5 GB file

32K 130 GB · 128K 139 GB

IQ4_NL

MiniMax M2.7

129 GB110.8 GB file

32K 133 GB · 128K 146 GB

Qwen3 235B A22B Thinking 2507

133 GB133.1 GB file

32K 136 GB · 128K 145 GB

Q4_1

MiniMax M2.7

129 GB143.5 GB file

32K 133 GB · 128K 146 GB

Qwen3 235B A22B Thinking 2507

133 GB147.2 GB file

32K 136 GB · 128K 145 GB

Q4_K_S

MiniMax M2.7

129 GB131.0 GB file

32K 133 GB · 128K 146 GB

Qwen3 235B A22B Thinking 2507

133 GB133.7 GB file

32K 136 GB · 128K 145 GB

Q4_K_L

MiniMax M2.7

141 GB139.3 GB file

32K 145 GB · 128K 157 GB

Qwen3 235B A22B Thinking 2507

not listed

Q5_0

MiniMax M2.7

143 GB157.5 GB file

32K 147 GB · 128K 160 GB

Qwen3 235B A22B Thinking 2507

not listed

Q5_1

MiniMax M2.7

158 GB171.7 GB file

32K 162 GB · 128K 174 GB

Qwen3 235B A22B Thinking 2507

not listed

Q5_K_S

MiniMax M2.7

158 GB159.0 GB file

32K 162 GB · 128K 174 GB

Qwen3 235B A22B Thinking 2507

162 GB161.9 GB file

32K 165 GB · 128K 175 GB

BF16

MiniMax M2.7

458 GB457.5 GB file

32K 462 GB · 128K 474 GB

Qwen3 235B A22B Thinking 2507

471 GB470.3 GB file

32K 474 GB · 128K 483 GB

How to run each

MiniMax M2.7

Ollama · Q4_K_M

$ollama run hf.co/unsloth/MiniMax-M2.7-GGUF:Q4_K_M

All ways to run MiniMax M2.7 →

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 →

Specifications

Specifications of MiniMax M2.7 and Qwen3 235B A22B Thinking 2507
Spec	MiniMax M2.7	Qwen3 235B A22B Thinking 2507
Publisher	MiniMax	Alibaba
Parameters	228.7B	235.1B
Active parameters	11B per token	22B per token
Architecture	MiniMaxM2ForCausalLM	Qwen3MoeForCausalLM
Context	200K tokens	256K tokens
Modalities	Chat, Function-calling	Chat, Function-calling
License	Other	Apache 2.0
Released	Apr 2026	Jul 2025

Frequently Asked Questions

Which is better, MiniMax M2.7 or Qwen3 235B A22B Thinking 2507?

MiniMax M2.7 and Qwen3 235B A22B Thinking 2507 match in llmrun Score, with values of 106.8 versus 108.1; neither fits 24 GB. Choose MiniMax M2.7 for ahead on the benchmarks and newer release; choose Qwen3 235B A22B Thinking 2507 for more permissive license.

Which needs less VRAM, MiniMax M2.7 or Qwen3 235B A22B Thinking 2507?

At Q4_K_M, MiniMax M2.7 requires 137.8 GB while Qwen3 235B A22B Thinking 2507 needs 141.6 GB, making MiniMax M2.7 the easier model to run on your local setup.

Can I run MiniMax M2.7 or Qwen3 235B A22B Thinking 2507 on a 16 GB GPU?

MiniMax M2.7 does not fit (smallest quant needs 65.3 GB); Qwen3 235B A22B Thinking 2507 does not fit (smallest quant needs 72.4 GB).

Which has a longer context window, MiniMax M2.7 or Qwen3 235B A22B Thinking 2507?

MiniMax M2.7 supports 204,800 tokens and Qwen3 235B A22B Thinking 2507 supports 262,144 tokens.