MiniMax M2 vs Inkling Small
Inkling Small leads llmrun Score 119.6 to 104.0; neither fits 24 GB.
Run Inkling Small in the cloud →
Model A · MiniMax
MiniMax M2228.7B · 11B active · 192K context · Other · Oct 2025
Model B · Thinking Machines
Inkling Small266.0B · 1.7B active · Apache 2.0 · Jul 2026
Choose MiniMax M2 if you want…
Fits a Mac 128 GB
Q3_K_L · 119.6 GB; Inkling Small needs 76.3 GB at its smallest quant
Also does function-calling
Inkling Small doesn't list it
Choose Inkling Small if you want…
Higher llmrun Score
119.6 vs 104.0
Also does vision
MiniMax M2 doesn't list it
More permissive license
Apache 2.0 vs Other
Newer release
Jul 2026 vs Oct 2025
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
Doesn't fit
smallest quant needs 65.3 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
12 GB
RTX 3060 12GB · 12 GB tier
MiniMax M2
Doesn't fit
smallest quant needs 65.3 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
MiniMax M2
Doesn't fit
smallest quant needs 65.3 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
24 GBreference
RTX 4090 · 24 GB tier
MiniMax M2
Doesn't fit
smallest quant needs 65.3 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
32 GB
RTX 5090 · 32 GB tier
MiniMax M2
Doesn't fit
smallest quant needs 65.3 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
48 GB
RTX A6000 · 48 GB tier
MiniMax M2
Doesn't fit
smallest quant needs 65.3 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
Mac 32 GB
Mac Mini M4 · Macs
MiniMax M2
Doesn't fit
smallest quant needs 65.3 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
Mac 64 GB
Mac Studio M4 Max · Macs
MiniMax M2
Doesn't fit
smallest quant needs 65.3 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
Mac 128 GB
Mac Studio M4 Max · Macs
MiniMax M2
Q3_K_L · ~37 tok/s
119.6 GB · up to 32Kbetter quant
Inkling Small
Q2_K · ~97 tok/s
116.2 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
Inkling Small
Agents
MiniMax M2
Inkling Small
no data
Math
MiniMax M2
no data
Inkling Small
Science
MiniMax M2
no data
Inkling Small
Reasoning
MiniMax M2
no data
Inkling Small
MiniMax M2 · #46 of 106 open models · #26 of 82 that fit ≤192 GB
Inkling Small · #16 of 106 open models · #6 of 82 that fit ≤192 GB
18 more boards (other shared and single-model boards)
MiniMax M2
1343.5#81/188 open
ArenaLMArena · Oct 2026
Inkling Small
1405.5#47/188 open
ArenaLMArena · Oct 2026
MiniMax M2
1297.1#47/55 open
ArenaLMArena · Oct 2026
Inkling Small
1409.1#29/55 open
ArenaLMArena · Oct 2026
Only MiniMax M2 (5)
- SWE-bench Verified61.0%
- Terminal-Bench30.0%
- MMLU-Pro82.0%
- SWE-bench Bash Only61.0%
- Vending-Bench 2160.6
Only Inkling Small (11)
- GPQA Diamond88.5%
- AIME 2024/202590.0%
- FrontierMath46.3%
- ARC-AGI-240.1%
- SciCode49.6%
- ARC-AGI84.0%
- SimpleQA19.1%
- FrontierMath Tier 417.1%
- CritPt8.3%
- Mystery Game Puzzles6.0%
- ProofBench6.0%
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
97.8 GB83.3 GB file
32K 102 GB · 128K 114 GB
Inkling Small
114 GB~113.0 GB file
32K 119 GB · 128K 136 GB
Q3_K_S
MiniMax M2
101 GB98.7 GB file
32K 105 GB · 128K 117 GB
Inkling Small
not listed
Q3_K_M
MiniMax M2
112 GB109.3 GB file
32K 116 GB · 128K 128 GB
Inkling Small
130 GB119.4 GB file
32K 136 GB · 128K 153 GB
Q4_0
MiniMax M2
115 GB129.5 GB file
32K 119 GB · 128K 131 GB
Inkling Small
not listed
Q4_K_M
MiniMax M2
138 GB138.3 GB file
32K 142 GB · 128K 154 GB
Inkling Small
160 GB162.5 GB file
32K 166 GB · 128K 182 GB
Q5_K_M
MiniMax M2
164 GB162.3 GB file
32K 167 GB · 128K 180 GB
Inkling Small
190 GB196.1 GB file
32K 195 GB · 128K 212 GB
Q6_K
MiniMax M2
189 GB187.8 GB file
32K 193 GB · 128K 206 GB
Inkling Small
220 GB218.9 GB file
32K 225 GB · 128K 242 GB
Q8_0
MiniMax M2
229 GB243.1 GB file
32K 233 GB · 128K 246 GB
Inkling Small
267 GB280.3 GB file
32K 272 GB · 128K 289 GB
15 more quants
IQ2_XXS
MiniMax M2
63.5 GB74.0 GB file
32K 67.4 GB · 128K 79.8 GB
Inkling Small
73.8 GB82.3 GB file
32K 79.1 GB · 128K 96.0 GB
IQ2_XS
MiniMax M2
69.2 GB63.1 GB file
32K 73.1 GB · 128K 85.6 GB
Inkling Small
not listed
IQ2_S
MiniMax M2
72.0 GB63.4 GB file
32K 75.9 GB · 128K 88.4 GB
Inkling Small
not listed
IQ2_M
MiniMax M2
77.7 GB78.1 GB file
32K 81.6 GB · 128K 94.1 GB
Inkling Small
90.4 GB82.4 GB file
32K 95.7 GB · 128K 113 GB
IQ3_XXS
MiniMax M2
89.2 GB93.6 GB file
32K 93.1 GB · 128K 106 GB
Inkling Small
104 GB97.9 GB file
32K 109 GB · 128K 126 GB
IQ3_XS
MiniMax M2
94.9 GB93.8 GB file
32K 98.8 GB · 128K 111 GB
Inkling Small
not listed
IQ3_S
MiniMax M2
97.8 GB98.7 GB file
32K 102 GB · 128K 114 GB
Inkling Small
114 GB107.5 GB file
32K 119 GB · 128K 136 GB
IQ3_M
MiniMax M2
103 GB104.0 GB file
32K 107 GB · 128K 120 GB
Inkling Small
not listed
Q3_K_L
MiniMax M2
118 GB108.2 GB file
32K 122 GB · 128K 134 GB
Inkling Small
not listed
IQ4_XS
MiniMax M2
123 GB121.9 GB file
32K 127 GB · 128K 140 GB
Inkling Small
144 GB127.4 GB file
32K 149 GB · 128K 166 GB
IQ4_NL
MiniMax M2
129 GB129.0 GB file
32K 133 GB · 128K 146 GB
Inkling Small
150 GB130.1 GB file
32K 156 GB · 128K 172 GB
Q4_1
MiniMax M2
129 GB143.2 GB file
32K 133 GB · 128K 146 GB
Inkling Small
not listed
Q4_K_S
MiniMax M2
129 GB130.0 GB file
32K 133 GB · 128K 146 GB
Inkling Small
150 GB152.3 GB file
32K 156 GB · 128K 172 GB
Q5_K_S
MiniMax M2
158 GB157.5 GB file
32K 162 GB · 128K 174 GB
Inkling Small
184 GB184.2 GB file
32K 189 GB · 128K 206 GB
BF16
MiniMax M2
458 GB457.5 GB file
32K 462 GB · 128K 474 GB
Inkling Small
533 GB527.4 GB file
32K 538 GB · 128K 555 GB
MiniMax M2
Ollama · Q4_K_M
ollama run hf.co/unsloth/MiniMax-M2-GGUF:Q4_K_MInkling Small
Ollama · Q4_K_M
ollama run hf.co/unsloth/Inkling-Small-GGUF:Q4_K_M| Spec | MiniMax M2 | Inkling Small |
|---|---|---|
| Publisher | MiniMax | Thinking Machines |
| Parameters | 228.7B | 266.0B |
| Active parameters | 11B per token | 1.7B per token |
| Architecture | MiniMaxM2ForCausalLM | InklingForConditionalGeneration |
| Context | 192K tokens | — |
| Modalities | Chat, Function-calling | Vision, Chat |
| License | Other | Apache 2.0 |
| Released | Oct 2025 | Jul 2026 |
Frequently Asked Questions
Which is better, MiniMax M2 or Inkling Small?
Inkling Small leads llmrun Score 119.6 to 104.0; neither fits 24 GB. Choose MiniMax M2 for fits a Mac 128 GB and also does function-calling; choose Inkling Small for higher llmrun Score and also does vision.
Which needs less VRAM, MiniMax M2 or Inkling Small?
At Q4_K_M, MiniMax M2 requires 137.8 GB while Inkling Small needs 160.2 GB, making MiniMax M2 the easier model to run on your local setup.
Can I run MiniMax M2 or Inkling Small on a 16 GB GPU?
MiniMax M2 does not fit (smallest quant needs 65.3 GB); Inkling Small does not fit (smallest quant needs 76.3 GB).