MiniMax M2.1 vs Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 leads llmrun Score 108.2 to 106.2 (ranges overlap); neither fits 24 GB.
Model A · MiniMax
MiniMax M2.1228.7B · 11B active · 192K context · Other · Dec 2025
Model B · Alibaba
Qwen3 235B A22B Thinking 2507235.1B · 22.2B active · 256K context · Apache 2.0 · Jul 2025
Choose MiniMax M2.1 if you want…
Newer release
Dec 2025 vs Jul 2025
Choose Qwen3 235B A22B Thinking 2507 if you want…
Higher llmrun Score
108.2 vs 106.2, ranges overlap
Longer context window
256K vs 192K tokens
Also does function-calling
MiniMax M2.1 doesn't list it
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%.
8 GB
RTX 4060 · 8 GB tier
MiniMax M2.1
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 M2.1
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 M2.1
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 M2.1
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 M2.1
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 M2.1
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 M2.1
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 M2.1
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 M2.1
Q4_0 · ~37 tok/s
116.7 GB · up to 64Kbetter quant
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).
Overall
MiniMax M2.1
Qwen3 235B A22B Thinking 2507
Coding
MiniMax M2.1
no data
Qwen3 235B A22B Thinking 2507
Science
MiniMax M2.1
no data
Qwen3 235B A22B Thinking 2507
Reasoning
MiniMax M2.1
no data
Qwen3 235B A22B Thinking 2507
MiniMax M2.1 · #38 of 100 open models · #21 of 78 that fit ≤192 GB
Qwen3 235B A22B Thinking 2507 · #33 of 100 open models · #16 of 78 that fit ≤192 GB
Benchmarks
1 shared board: MiniMax M2.1 leads 1, Qwen3 235B A22B Thinking 2507 leads 0 · Benchmarks imported Oct 2026
MiniMax M2.1
88.0%#1/145 open
IndependentTIGER-Lab
Qwen3 235B A22B Thinking 2507
84.5%#11/145 open
IndependentTIGER-Lab
15 more boards (other shared and single-model boards)
MiniMax M2.1
1384.4#59/187 open
ArenaLMArena · Oct 2026
Qwen3 235B A22B Thinking 2507
1399.8#49/187 open
ArenaLMArena · Oct 2026
Only MiniMax M2.1 (3)
- Terminal-Bench36.6%
- LMArena WebDev1384.3
- ALE-Bench623.8
Only Qwen3 235B A22B Thinking 2507 (11)
- GPQA Diamond80.0%
- AIME 2024/202586.7%
- SciCode41.4%
- SimpleQA40.4%
- WeirdML41.0%
- CritPt0.0%
- DTBench80.3%
- Fiction.LiveBench75.0%
- LMCA29.3%
- Mystery Game Puzzles9.0%
- Vending-Bench 2-11.3
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
MiniMax M2.1
97.8 GB83.3 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 M2.1
101 GB98.7 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 M2.1
112 GB109.3 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 M2.1
115 GB129.5 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 M2.1
138 GB138.3 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 M2.1
164 GB162.3 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 M2.1
189 GB187.8 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 M2.1
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
14 more quants
IQ2_XXS
MiniMax M2.1
63.5 GB74.1 GB file
32K 67.4 GB · 128K 79.8 GB
Qwen3 235B A22B Thinking 2507
not listed
IQ2_XS
MiniMax M2.1
not listed
Qwen3 235B A22B Thinking 2507
71.0 GB65.6 GB file
32K 74.0 GB · 128K 83.5 GB
IQ2_S
MiniMax M2.1
not listed
Qwen3 235B A22B Thinking 2507
74.0 GB66.1 GB file
32K 76.9 GB · 128K 86.4 GB
IQ2_M
MiniMax M2.1
77.8 GB78.1 GB file
32K 81.7 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 M2.1
89.2 GB93.3 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
IQ3_XS
MiniMax M2.1
not listed
Qwen3 235B A22B Thinking 2507
97.5 GB96.9 GB file
32K 100 GB · 128K 110 GB
IQ3_M
MiniMax M2.1
not listed
Qwen3 235B A22B Thinking 2507
106 GB107.3 GB file
32K 109 GB · 128K 119 GB
Q3_K_L
MiniMax M2.1
not listed
Qwen3 235B A22B Thinking 2507
121 GB111.2 GB file
32K 124 GB · 128K 133 GB
IQ4_XS
MiniMax M2.1
123 GB121.9 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 M2.1
129 GB129.0 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 M2.1
129 GB143.2 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 M2.1
129 GB130.0 GB file
32K 133 GB · 128K 146 GB
Qwen3 235B A22B Thinking 2507
133 GB133.7 GB file
32K 136 GB · 128K 145 GB
Q5_K_S
MiniMax M2.1
158 GB157.5 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 M2.1
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
MiniMax M2.1
Ollama · Q4_K_M
ollama run hf.co/unsloth/MiniMax-M2.1-GGUF:Q4_K_MQwen3 235B A22B Thinking 2507
Ollama · Q4_K_M
ollama run hf.co/unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF:Q4_K_M| Spec | MiniMax M2.1 | 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 | 192K tokens | 256K tokens |
| Modalities | Chat | Chat, Function-calling |
| License | Other | Apache 2.0 |
| Released | Dec 2025 | Jul 2025 |
Frequently Asked Questions
Which is better, MiniMax M2.1 or Qwen3 235B A22B Thinking 2507?
Qwen3 235B A22B Thinking 2507 leads llmrun Score 108.2 to 106.2 (ranges overlap); neither fits 24 GB. Choose MiniMax M2.1 for newer release; choose Qwen3 235B A22B Thinking 2507 for higher llmrun Score and longer context window.
Which needs less VRAM, MiniMax M2.1 or Qwen3 235B A22B Thinking 2507?
At Q4_K_M, MiniMax M2.1 requires 137.8 GB while Qwen3 235B A22B Thinking 2507 needs 141.6 GB, making MiniMax M2.1 the easier model to run on your local setup.
Can I run MiniMax M2.1 or Qwen3 235B A22B Thinking 2507 on a 16 GB GPU?
MiniMax M2.1 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 M2.1 or Qwen3 235B A22B Thinking 2507?
MiniMax M2.1 supports 196,608 tokens and Qwen3 235B A22B Thinking 2507 supports 262,144 tokens.