MiniMax M2.7 vs GPT OSS 120B
MiniMax M2.7 leads llmrun Score 106.8 to 97.6; neither fits 24 GB.
Model A · MiniMax
MiniMax M2.7228.7B · 11B active · 200K context · Other · Apr 2026
Model B · OpenAI
GPT OSS 120B116.8B · 5.8B active · 128K context · Apache 2.0 · Aug 2025
Choose MiniMax M2.7 if you want…
Higher llmrun Score
106.8 vs 97.6
Longer context window
200K vs 128K tokens
Newer release
Apr 2026 vs Aug 2025
Choose GPT OSS 120B if you want…
Fits a Mac 64 GB
Q4_0 · 59.1 GB; MiniMax M2.7 needs 65.3 GB at its smallest quant
Lighter on memory
70.5 vs 137.8 GB at Q4_K_M
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 M2.7
Doesn't fit
smallest quant needs 65.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
12 GB
RTX 3060 12GB · 12 GB tier
MiniMax M2.7
Doesn't fit
smallest quant needs 65.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
MiniMax M2.7
Doesn't fit
smallest quant needs 65.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
24 GBreference
RTX 4090 · 24 GB tier
MiniMax M2.7
Doesn't fit
smallest quant needs 65.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
32 GB
RTX 5090 · 32 GB tier
MiniMax M2.7
Doesn't fit
smallest quant needs 65.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
48 GB
RTX A6000 · 48 GB tier
MiniMax M2.7
Doesn't fit
smallest quant needs 65.3 GB
GPT OSS 120B
IQ2_M · ~169 tok/s
40.2 GB · up to 128Kfits
Mac 32 GB
Mac Mini M4 · Macs
MiniMax M2.7
Doesn't fit
smallest quant needs 65.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
Mac 64 GB
Mac Studio M4 Max · Macs
MiniMax M2.7
Doesn't fit
smallest quant needs 65.3 GB
GPT OSS 120B
Q4_0 · ~68 tok/s
59.1 GB · up to 64Kfits
Mac 128 GB
Mac Studio M4 Max · Macs
MiniMax M2.7
Q3_K_L · ~37 tok/s
119.6 GB · up to 32K
GPT OSS 120B
Q4_K_M · ~61 tok/s
70.8 GB · up to 128Kmore headroom
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
MiniMax M2.7
GPT OSS 120B
Coding
MiniMax M2.7
GPT OSS 120B
Agents
MiniMax M2.7
no data
GPT OSS 120B
Science
MiniMax M2.7
GPT OSS 120B
Reasoning
MiniMax M2.7
no data
GPT OSS 120B
MiniMax M2.7 · #34 of 92 open models · #18 of 71 that fit ≤192 GB
GPT OSS 120B · #54 of 92 open models · #23 of 54 that fit ≤96 GB
Benchmarks
5 shared boards: MiniMax M2.7 leads 3, GPT OSS 120B leads 2 · Benchmarks imported Oct 2026
MiniMax M2.7
1415.0#39/186 open
ArenaLMArena · Oct 2026
GPT OSS 120B
1351.8#74/186 open
ArenaLMArena · Oct 2026
MiniMax M2.7
45.1%#2/16 open
Lab-reportedEpoch AI · Mar 2026
GPT OSS 120B
18.7%#14/16 open
Lab-reportedEpoch AI · Aug 2025
MiniMax M2.7
47.0%#17/65 open
Lab-reportedEpoch AI · Mar 2026
GPT OSS 120B
36.0%#39/65 open
Lab-reportedEpoch AI · Aug 2025
MiniMax M2.7
37.0%#30/46 open
IndependentEpoch AI · Mar 2026
GPT OSS 120B
48.2%#11/46 open
IndependentEpoch AI · Aug 2025
MiniMax M2.7
0.6%#37/65 open
Lab-reportedEpoch AI · Mar 2026
GPT OSS 120B
1.1%#31/65 open
Lab-reportedEpoch AI · Aug 2025
18 more boards (other shared and single-model boards)
MiniMax M2.7
599.3#26/42 open
Lab-reportedEpoch AI · Mar 2026
GPT OSS 120B
575.6#28/42 open
Lab-reportedEpoch AI · Aug 2025
Only MiniMax M2.7 (2)
- LMArena WebDev1397.9
- ProofBench3.0%
Only GPT OSS 120B (15)
- SWE-bench Verified26.0%
- GPQA Diamond75.8%
- AIME 2024/202588.9%
- MMLU-Pro80.8%
- Aider Polyglot41.8%
- SWE-bench Bash Only26.0%
- SimpleBench22.1%
- Chess Puzzles20.0%
- DTBench76.3%
- LMCA22.1%
- APEX-Agents4.4%
- Fiction.LiveBench44.4%
- Mystery Game Puzzles2.0%
- Vending-Bench 2-21.5
- Surface Evolver Bench25.0%
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 M2.7
97.8 GB80.1 GB file
32K 102 GB · 128K 114 GB
GPT OSS 120B
50.1 GB62.6 GB file
32K 50.8 GB · 128K 53.4 GB
Q3_K_S
MiniMax M2.7
101 GB93.6 GB file
32K 105 GB · 128K 117 GB
GPT OSS 120B
51.5 GB62.6 GB file
32K 52.3 GB · 128K 54.8 GB
Q3_K_M
MiniMax M2.7
112 GB101.2 GB file
32K 116 GB · 128K 128 GB
GPT OSS 120B
57.4 GB62.6 GB file
32K 58.1 GB · 128K 60.7 GB
Q4_0
MiniMax M2.7
115 GB129.8 GB file
32K 119 GB · 128K 131 GB
GPT OSS 120B
58.8 GB62.6 GB file
32K 59.6 GB · 128K 62.1 GB
Q4_K_M
MiniMax M2.7
138 GB140.2 GB file
32K 142 GB · 128K 154 GB
GPT OSS 120B
70.5 GB62.8 GB file
32K 71.3 GB · 128K 73.8 GB
Q5_K_M
MiniMax M2.7
164 GB168.8 GB file
32K 167 GB · 128K 180 GB
GPT OSS 120B
83.7 GB62.9 GB file
32K 84.4 GB · 128K 86.9 GB
Q6_K
MiniMax M2.7
189 GB188.1 GB file
32K 193 GB · 128K 206 GB
GPT OSS 120B
96.8 GB63.3 GB file
32K 97.5 GB · 128K 100 GB
Q8_0
MiniMax M2.7
229 GB243.1 GB file
32K 233 GB · 128K 246 GB
GPT OSS 120B
117 GB~116.8 GB file
32K 118 GB · 128K 121 GB
19 more quants
IQ2_XXS
MiniMax M2.7
63.5 GB65.4 GB file
32K 67.4 GB · 128K 79.8 GB
GPT OSS 120B
not listed
IQ2_XS
MiniMax M2.7
69.2 GB67.9 GB file
32K 73.1 GB · 128K 85.6 GB
GPT OSS 120B
not listed
IQ2_S
MiniMax M2.7
72.0 GB69.1 GB file
32K 75.9 GB · 128K 88.4 GB
GPT OSS 120B
not listed
IQ2_M
MiniMax M2.7
77.7 GB70.1 GB file
32K 81.6 GB · 128K 94.1 GB
GPT OSS 120B
39.8 GB~39.4 GB file
32K 40.6 GB · 128K 43.1 GB
IQ3_XXS
MiniMax M2.7
89.2 GB80.1 GB file
32K 93.1 GB · 128K 106 GB
GPT OSS 120B
not listed
Q2_K_S
MiniMax M2.7
92.0 GB77.6 GB file
32K 95.9 GB · 128K 108 GB
GPT OSS 120B
not listed
IQ3_XS
MiniMax M2.7
94.9 GB104.1 GB file
32K 98.8 GB · 128K 111 GB
GPT OSS 120B
not listed
IQ3_S
MiniMax M2.7
97.8 GB83.6 GB file
32K 102 GB · 128K 114 GB
GPT OSS 120B
not listed
IQ3_M
MiniMax M2.7
103 GB108.8 GB file
32K 107 GB · 128K 120 GB
GPT OSS 120B
53.0 GB62.7 GB file
32K 53.7 GB · 128K 56.3 GB
Q3_K_L
MiniMax M2.7
118 GB108.5 GB file
32K 122 GB · 128K 134 GB
GPT OSS 120B
60.3 GB62.6 GB file
32K 61.0 GB · 128K 63.6 GB
IQ4_XS
MiniMax M2.7
123 GB108.4 GB file
32K 127 GB · 128K 140 GB
GPT OSS 120B
63.2 GB62.7 GB file
32K 64.0 GB · 128K 66.5 GB
IQ4_NL
MiniMax M2.7
129 GB110.8 GB file
32K 133 GB · 128K 146 GB
GPT OSS 120B
66.1 GB62.7 GB file
32K 66.9 GB · 128K 69.4 GB
Q4_1
MiniMax M2.7
129 GB143.5 GB file
32K 133 GB · 128K 146 GB
GPT OSS 120B
66.1 GB62.7 GB file
32K 66.9 GB · 128K 69.4 GB
Q4_K_S
MiniMax M2.7
129 GB131.0 GB file
32K 133 GB · 128K 146 GB
GPT OSS 120B
66.1 GB62.8 GB file
32K 66.9 GB · 128K 69.4 GB
Q4_K_L
MiniMax M2.7
141 GB139.3 GB file
32K 145 GB · 128K 157 GB
GPT OSS 120B
72.0 GB63.1 GB file
32K 72.7 GB · 128K 75.3 GB
Q5_0
MiniMax M2.7
143 GB157.5 GB file
32K 147 GB · 128K 160 GB
GPT OSS 120B
not listed
Q5_1
MiniMax M2.7
158 GB171.7 GB file
32K 162 GB · 128K 174 GB
GPT OSS 120B
not listed
Q5_K_S
MiniMax M2.7
158 GB159.0 GB file
32K 162 GB · 128K 174 GB
GPT OSS 120B
80.7 GB62.9 GB file
32K 81.5 GB · 128K 84.0 GB
BF16
MiniMax M2.7
458 GB457.5 GB file
32K 462 GB · 128K 474 GB
GPT OSS 120B
234 GB~233.7 GB file
32K 235 GB · 128K 237 GB
MiniMax M2.7
Ollama · Q4_K_M
ollama run hf.co/unsloth/MiniMax-M2.7-GGUF:Q4_K_MGPT OSS 120B
Ollama · Q4_K_M
ollama run hf.co/unsloth/gpt-oss-120b-GGUF:Q4_K_M| Spec | MiniMax M2.7 | GPT OSS 120B |
|---|---|---|
| Publisher | MiniMax | OpenAI |
| Parameters | 228.7B | 116.8B |
| Active parameters | 11B per token | 5.8B per token |
| Architecture | MiniMaxM2ForCausalLM | GptOssForCausalLM |
| Context | 200K tokens | 128K tokens |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | Other | Apache 2.0 |
| Released | Apr 2026 | Aug 2025 |
Frequently Asked Questions
Which is better, MiniMax M2.7 or GPT OSS 120B?
MiniMax M2.7 leads llmrun Score 106.8 to 97.6; neither fits 24 GB. Choose MiniMax M2.7 for higher llmrun Score and longer context window; choose GPT OSS 120B for fits a Mac 64 GB and lighter on memory.
Which needs less VRAM, MiniMax M2.7 or GPT OSS 120B?
At Q4_K_M, MiniMax M2.7 requires 137.8 GB while GPT OSS 120B needs 70.5 GB, making GPT OSS 120B the easier model to run on your local setup.
Can I run MiniMax M2.7 or GPT OSS 120B on a 16 GB GPU?
MiniMax M2.7 does not fit (smallest quant needs 65.3 GB); GPT OSS 120B does not fit (smallest quant needs 40.2 GB).
Which has a longer context window, MiniMax M2.7 or GPT OSS 120B?
MiniMax M2.7 supports 204,800 tokens and GPT OSS 120B supports 131,072 tokens.