底部赞助展示区
Contact us 适合多赞助商长期展示
Loading…
适合多赞助商长期展示
Unsloth has released dynamic GGUF quantizations for MiniMax M3.1 Flash. Its 143.9GB 2-bit build reached 91.5% weighted top-1 token agreement across seven evaluation categories, lowering the hardware barrier for local use.
Unsloth says the 143.9GB UD-Q2_K_XL quantization of MiniMax-M3.1-Flash achieved 91.5% weighted top-1 token agreement across coding, math, chat, tool use, multilingual tasks, reasoning, and agentic workloads. The figure measures how closely the quantized model matches the original model’s preferred token choices; it is not a universal accuracy score.
MiniMax M3.1 Flash is a mixture-of-experts model with roughly 428 billion total parameters and about 23 billion active parameters. Unsloth recommends planning for more than 160GB of combined RAM and VRAM, or equivalent unified memory, for the 2-bit build. Actual requirements vary with context length and concurrency.
The model accepts text, image, and video inputs and incorporates sparse attention along with quantization-aware training for attention and routed experts. The GGUF releases make local inference more accessible on high-memory systems, but users should still verify runtime compatibility and hardware requirements before deployment.
Source review does not guarantee permanent accuracy. Consider the original source, observation time, and later corrections.
| NL2Repo-Bench | 61.2 | 68.2 | 65.4 | 58.0 | 58.0 | 56.8 | 75.3 | | SWE Refactor Bench | 23.0 | — | 11.8 | 19.5 | 10.4 | 28.5 | 31.0 | | CyberGym | 82.2 | — | — | 80.0 | 84.5 | 83.6 | — | | BabyVision (with tools) | 91.0 | 92.5 | 89.6 | 85.7 | — | 88.9 | 94.1 | | HLE (without tools) | 43.4 | 42.6 | 39.2 | 43.5 | 42.3 | 49.5 | 55.6 | | CharXiv RQ | 82.5 | — | 69.0 | 84.8 | — | 85.2 | 83.7 | [...] | Benchmark | MiniMax M3.1 Flash | DeepSeek V4.1 Flash-1017 | DeepSeek V4.1 Flash | Kimi K3 | GLM-5.3 | GPT-5.6 Sol | Opus 5 | --- --- --- --- | | Automation-Bench v1.0.6 | 62.8 | 60.5 | 54.8 | 46.7 | 48.8 | 45.8 | 50.3 | | BankerToolBench | 76.2 | — | 73.7 | 69.1 | 74.5 | 74.6 | 76.2 | | GDP.pdf AA | 20.8 | — | 12.8 | 22.0 | 11.2 | 27.2 | 21.6 | | Terminal Bench 4.0 | 38.1 | 42.3 | 31.2 | 12.6 | 37.9 | 39.9 | 51.8 | | LOCA-Bench 256K | 60.3 | — | — | 49.7 | 50.3 | 60.0 | 53.7 | | Agents’ Last Exam | 29.6 | — | — | 28.3 | — | 30.6 | 32.2 | | OSWorld 2.0 | 61.7 | — | 54.3 | 58.3 | — | 65.7
| Model | Total / active | Licence (points) | Index min. RAM | M3 Ultra | M5 Ultra | Score (rank) | --- --- --- | MiMo-V2.6-Flash | 309B / 15B | MIT (10) | 170 GB | community59 tok/s | community62 tok/s | 78 (#7) | | DeepSeek V4.1 Flash | 552B / 16B | MIT (10) | 434 GB | community20 tok/s | estimated~29 tok/s | 70 (#17) | | MiniMax-M3 | 428B / 23B | MiniMax Community (4) | 162 GB | community29 tok/s | estimated~42 tok/s | 65 (#44) | | Muse Spark Open | 816B / 42B | Muse Model License (5) | 342 GB | sourced18 tok/s | estimated~31 tok/s | 65 (#45) | | MiniMax-M3.1-Flash | 428B / 23B | MiniMax Community (4) | 189 GB | community25 tok/s | community35 tok/s | 64 (#53) |
Our 129.4GB 1-bit achieves ~89.9% top-1 accuracy; 143.9GB 2-bit reaches 91.5%, and 249.4 GB 4-bit UD-Q4\_K\_XL 98.0%. On coding, Q2 reaches 91.2% and Q4 97.6%. We weighted quant performance across seven categories: coding, math, chat, tools, multilingual, reasoning and agentic use. Thank you MiniMax for day-zero access. ### ⚙️ Usage Guide MiniMax-M3.1-Flash supports text, images and video and adds sparse attention across all layers, QAT for attention and routed experts, and DSpark. For 2-bit UD-Q2\_K\_XL, budget 160GB+ RAM + VRAM (or unified memory); for 4-bit UD-Q4\_K\_XL, budget 256GB+. These planning estimates assume 16K text context and one parallel slot. [...] Top-1 agreement by quant: Quant File size General chat top-1 Math top-1 `UD-IQ1_M` 129.4 GB 86.2% 94.9% `UD-IQ2_XXS` 134.9 GB 87.5% 95.3% `UD-Q2_K_XL` 143.9 GB 88.5% 95.7% `UD-IQ3_XXS` 160.0 GB 89.9% 96.3% `UD-IQ3_S` 175.5 GB 91.2% 96.8% `UD-Q3_K_XL` 194.0 GB 92.6% 97.4% `UD-Q4_K_XL` 249.4 GB
| 552B / 8B prefill, 16B decode (NVIDIA card) | 2.8T / 104B (HF) | ~744B / ~40B, shared GLM-5 base | | Context | 1M | 1M (DeepSeek docs) | 1,048,576 | 1,048,576 (Cloudflare) | | Inputs | Text, image, video | Text, image | Text, image | Text | | Weights / license | Due Oct 23; license not disclosed | Open, MIT | Open, Kimi K3 License | Open weights | | API price in / out (1M) | $0.15 / $0.60 flat | $0.30 / $1.20 peak; half off-peak | $3.00 / $15.00 | $1.40 / $4.40 | | Self-host hardware | Not disclosed | Not disclosed | MXFP4 weights; vLLM, SGLang | Not disclosed | | Automation-Bench v1.0.6\ | 62.2 | 54.8 | 46.7 | 48.8 | | DeepSWE v1.1\ | 73.7 | 74.2 | 67.5 | 66.9 | | Terminal Bench 4.0\ | 38.1 | 31.2 | 12.6 | 37.9 | | BabyVision (w/ tools)\ | 91.0 | 89.6 | 85.7 | Not reported | [...] The model accepts text, image and video input and returns text. The context window is 1,000,000 tokens. Those parameter totals match MiniMax M3, which ships at ~428B total and ~23B active. MiniMax has not
| 552B / 8B prefill, 16B decode (NVIDIA card) | 2.8T / 104B (HF) | ~744B / ~40B, shared GLM-5 base | | Context | 1M | 1M (DeepSeek docs) | 1,048,576 | 1,048,576 (Cloudflare) | | Inputs | Text, image, video | Text, image | Text, image | Text | | Weights / license | Due Oct 23; license not disclosed | Open, MIT | Open, Kimi K3 License | Open weights | | API price in / out (1M) | $0.15 / $0.60 flat | $0.30 / $1.20 peak; half off-peak | $3.00 / $15.00 | $1.40 / $4.40 | | Self-host hardware | Not disclosed | Not disclosed | MXFP4 weights; vLLM, SGLang | Not disclosed | | Automation-Bench v1.0.6\ | 62.2 | 54.8 | 46.7 | 48.8 | | DeepSWE v1.1\ | 73.7 | 74.2 | 67.5 | 66.9 | | Terminal Bench 4.0\ | 38.1 | 31.2 | 12.6 | 37.9 | | BabyVision (w/ tools)\ | 91.0 | 89.6 | 85.7 | Not reported | [...] Open Source Close Welcome Bar ### Get AI Dev Signals The newsletter 70,000+ AI builders read. Model releases, tools and research, without the hype. Exit mobile version
Title: MiniMax M3.1 Exposed: The 428B MoE Model That FORCES You to Think! # MiniMax M3.1 Exposed: The 428B MoE Model That FORCES You to Think! Think you know how LLM scaling works? MiniMax M3.1 Flash-Preview just flipped the script on open inference. By ditching raw parameter bloat for dynamic test-time compute governance, this system delivers an insane sub-300ms Time-To-First-Token (TTFT) across a massive 1,000,000-token context window! In this exclusive deep systems teardown, we get under the hood of MiniMax's newest powerhouse:. • The 428B MoE Monster: Why activating just 23B parameters (5.37%) beats brute-force compute. • MiniMax Sparse Attention (MSA): How O(N*B*d) scaling eliminates quadratic latency crashes. • The HTTP 400 Shock: Anthropic & OpenAI let you turn off thinking—MiniMax makes reasoning mandatory! • Triton Kernel Magic: 9x prefill speedup and 15x decoding acceleration in action. • Real-World Agent Chaos: 1,959 tool calls that optimized CUDA FP8 kernels from 7.6% to 71