MiniMax M3 vs Inkling Small
Inkling Small leads llmrun Score 119.6 to 112.5; neither fits 24 GB.
Model A · MiniMax
MiniMax M3427.0B · 19.8B active · 1M context · Other · Jun 2026
Model B · Thinking Machines
Inkling Small266.0B · 1.7B active · Apache 2.0 · Jul 2026
Choose Inkling Small if you want…
Higher llmrun Score
119.6 vs 112.5
Stronger at reasoning
122.6 vs 107.9
Stronger at math
117.1 vs 106.1
Fits a Mac 128 GB
IQ3_S · 116.2 GB; MiniMax M3 needs 119.2 GB at its smallest quant
Lighter on memory
160.2 vs 256.7 GB at Q4_K_M
Also does chat
MiniMax M3 doesn't list it
MiniMax M3: no clear edge over Inkling Small in the data we have.
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 M3
Doesn't fit
smallest quant needs 119.2 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
12 GB
RTX 3060 12GB · 12 GB tier
MiniMax M3
Doesn't fit
smallest quant needs 119.2 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
MiniMax M3
Doesn't fit
smallest quant needs 119.2 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
24 GBreference
RTX 4090 · 24 GB tier
MiniMax M3
Doesn't fit
smallest quant needs 119.2 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
32 GB
RTX 5090 · 32 GB tier
MiniMax M3
Doesn't fit
smallest quant needs 119.2 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
48 GB
RTX A6000 · 48 GB tier
MiniMax M3
Doesn't fit
smallest quant needs 119.2 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
Mac 32 GB
Mac Mini M4 · Macs
MiniMax M3
Doesn't fit
smallest quant needs 119.2 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
Mac 64 GB
Mac Studio M4 Max · Macs
MiniMax M3
Doesn't fit
smallest quant needs 119.2 GB
Inkling Small
Doesn't fit
smallest quant needs 76.3 GB
Mac 128 GB
Mac Studio M4 Max · Macs
MiniMax M3
IQ2_XXS · ~38 tok/s
119.2 GB · up to 64K
Inkling Small
IQ3_S · ~97 tok/s
116.2 GB · up to 32Kbetter quant
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
MiniMax M3
Inkling Small
Coding
MiniMax M3
Inkling Small
no data
Agents
MiniMax M3
Inkling Small
no data
Math
MiniMax M3
Inkling Small
Science
MiniMax M3
Inkling Small
Reasoning
MiniMax M3
Inkling Small
MiniMax M3 · #21 of 100 open models · #18 of 96 that fit ≤512 GB
Inkling Small · #13 of 100 open models · #5 of 78 that fit ≤192 GB
MiniMax M3
90.9%#6/98 open
IndependentEpoch AI · Jun 2026
Inkling Small
88.5%#13/98 open
IndependentEpoch AI · Jul 2026
MiniMax M3
71.1%#27/86 open
IndependentEpoch AI · Jun 2026
Inkling Small
90.0%#14/86 open
IndependentEpoch AI · Jul 2026
MiniMax M3
47.1%#17/66 open
Lab-reportedEpoch AI · Jun 2026
Inkling Small
49.6%#14/66 open
Lab-reportedEpoch AI · Jul 2026
MiniMax M3
3.7%#20/66 open
Lab-reportedEpoch AI · Jun 2026
Inkling Small
8.3%#12/66 open
Lab-reportedEpoch AI · Jul 2026
MiniMax M3
8.0%#14/18 open
IndependentEpoch AI · Jun 2026
Inkling Small
6.0%#17/18 open
IndependentEpoch AI · Jul 2026
MiniMax M3
18.0%#13/26 open
Lab-reportedEpoch AI · Jun 2026
Inkling Small
6.0%#19/26 open
Lab-reportedEpoch AI · Jul 2026
27 more boards (other shared and single-model boards)
MiniMax M3
1441.3#19/187 open
ArenaLMArena · Oct 2026
Inkling Small
1404.0#46/187 open
ArenaLMArena · Oct 2026
MiniMax M3
1482.5#17/52 open
ArenaLMArena · Oct 2026
Inkling Small
1409.1#27/52 open
ArenaLMArena · Oct 2026
Only MiniMax M3 (20)
- LiveBench Coding68.2
- LiveBench Reasoning74.5
- LiveBench Math77.0
- SimpleBench45.8%
- FrontierCode14.7%
- APEX-Agents37.7%
- Chess Puzzles13.0%
- DTBench78.9%
- ForecastBench61.3
- LiveBench 2026 Reasoning74.5
- LMCA33.7%
- Vending-Bench 22157.8
- LiveBench 2026 Browser8.0
- LiveBench 2026 Data Analysis76.2
- ALE-Bench640.0
- LiveBench 2026 Coding70.9
- LiveBench 2026 Long-Horizon12.4
- Surface Evolver Bench55.0%
- LiveBench 2026 Design66.2
- LiveBench 2026 Research68.0
Only Inkling Small (5)
- FrontierMath46.3%
- ARC-AGI-240.1%
- ARC-AGI84.0%
- SimpleQA19.1%
- FrontierMath Tier 417.1%
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 M3
182 GB151.9 GB file
32K 185 GB · 128K 194 GB
Inkling Small
114 GB~113.0 GB file
32K 119 GB · 128K 136 GB
Q3_K_S
MiniMax M3
187 GB187.3 GB file
32K 190 GB · 128K 199 GB
Inkling Small
not listed
Q3_K_M
MiniMax M3
209 GB195.5 GB file
32K 212 GB · 128K 221 GB
Inkling Small
130 GB119.4 GB file
32K 136 GB · 128K 153 GB
Q4_0
MiniMax M3
214 GB243.6 GB file
32K 217 GB · 128K 226 GB
Inkling Small
not listed
Q4_K_M
MiniMax M3
257 GB264.9 GB file
32K 260 GB · 128K 269 GB
Inkling Small
160 GB162.5 GB file
32K 166 GB · 128K 182 GB
Q5_K_M
MiniMax M3
305 GB318.7 GB file
32K 308 GB · 128K 317 GB
Inkling Small
190 GB196.1 GB file
32K 195 GB · 128K 212 GB
Q6_K
MiniMax M3
353 GB355.3 GB file
32K 356 GB · 128K 365 GB
Inkling Small
220 GB218.9 GB file
32K 225 GB · 128K 242 GB
Q8_0
MiniMax M3
428 GB453.6 GB file
32K 430 GB · 128K 439 GB
Inkling Small
267 GB280.3 GB file
32K 272 GB · 128K 289 GB
15 more quants
IQ2_XXS
MiniMax M3
118 GB134.9 GB file
32K 121 GB · 128K 130 GB
Inkling Small
73.8 GB82.3 GB file
32K 79.1 GB · 128K 96.0 GB
IQ2_XS
MiniMax M3
129 GB129.5 GB file
32K 131 GB · 128K 140 GB
Inkling Small
not listed
IQ2_S
MiniMax M3
134 GB132.1 GB file
32K 137 GB · 128K 146 GB
Inkling Small
not listed
IQ2_M
MiniMax M3
145 GB135.1 GB file
32K 147 GB · 128K 157 GB
Inkling Small
90.4 GB82.4 GB file
32K 95.7 GB · 128K 113 GB
IQ3_XXS
MiniMax M3
166 GB160.3 GB file
32K 169 GB · 128K 178 GB
Inkling Small
104 GB97.9 GB file
32K 109 GB · 128K 126 GB
IQ3_XS
MiniMax M3
177 GB196.4 GB file
32K 179 GB · 128K 189 GB
Inkling Small
not listed
IQ3_S
MiniMax M3
182 GB175.6 GB file
32K 185 GB · 128K 194 GB
Inkling Small
114 GB107.5 GB file
32K 119 GB · 128K 136 GB
IQ3_M
MiniMax M3
193 GB205.5 GB file
32K 195 GB · 128K 205 GB
Inkling Small
not listed
Q3_K_L
MiniMax M3
219 GB205.0 GB file
32K 222 GB · 128K 231 GB
Inkling Small
not listed
IQ4_XS
MiniMax M3
230 GB208.5 GB file
32K 233 GB · 128K 242 GB
Inkling Small
144 GB127.4 GB file
32K 149 GB · 128K 166 GB
IQ4_NL
MiniMax M3
241 GB212.7 GB file
32K 244 GB · 128K 253 GB
Inkling Small
150 GB130.1 GB file
32K 156 GB · 128K 172 GB
Q4_1
MiniMax M3
241 GB268.9 GB file
32K 244 GB · 128K 253 GB
Inkling Small
not listed
Q4_K_S
MiniMax M3
241 GB248.6 GB file
32K 244 GB · 128K 253 GB
Inkling Small
150 GB152.3 GB file
32K 156 GB · 128K 172 GB
Q5_K_S
MiniMax M3
294 GB299.7 GB file
32K 297 GB · 128K 306 GB
Inkling Small
184 GB184.2 GB file
32K 189 GB · 128K 206 GB
BF16
MiniMax M3
855 GB852.9 GB file
32K 857 GB · 128K 866 GB
Inkling Small
533 GB527.4 GB file
32K 538 GB · 128K 555 GB
MiniMax M3
Ollama · Q4_K_M
ollama run hf.co/unsloth/MiniMax-M3-GGUF:Q4_K_MInkling Small
Ollama · Q4_K_M
ollama run hf.co/unsloth/Inkling-Small-GGUF:Q4_K_M| Spec | MiniMax M3 | Inkling Small |
|---|---|---|
| Publisher | MiniMax | Thinking Machines |
| Parameters | 427.0B | 266.0B |
| Active parameters | 20B per token | 1.7B per token |
| Architecture | MiniMaxM3SparseForConditionalGeneration | InklingForConditionalGeneration |
| Context | 1M tokens | — |
| Modalities | Vision, Function-calling | Vision, Chat, Function-calling |
| License | Other | Apache 2.0 |
| Released | Jun 2026 | Jul 2026 |
Frequently Asked Questions
Which is better, MiniMax M3 or Inkling Small?
Inkling Small leads llmrun Score 119.6 to 112.5; neither fits 24 GB. Choose Inkling Small for higher llmrun Score and stronger at reasoning.
Which needs less VRAM, MiniMax M3 or Inkling Small?
At Q4_K_M, MiniMax M3 requires 256.7 GB while Inkling Small needs 160.2 GB, making Inkling Small the easier model to run on your local setup.
Can I run MiniMax M3 or Inkling Small on a 16 GB GPU?
MiniMax M3 does not fit (smallest quant needs 119.2 GB); Inkling Small does not fit (smallest quant needs 76.3 GB).