MiniMaxAI/MiniMax-M3
Image-Text-to-Text ā¢ 427B ā¢ Updated ā¢ 6.64k ā¢ ā¢ 477
Yune Leou
leouon
AI & ML interests
None yet
Recent Activity
liked a model 2 days ago
MiniMaxAI/MiniMax-M3 liked a model 3 days ago
DarkArtsForge/Helix-SCE-12B-jh liked a model 3 days ago
OpenYourMind/OpenYourMind-NVIDIA-Nemotron-3-Ultra-550B-A55B-abliterated-uncensoredOrganizations
None yet
liked a
model 2 days ago
liked 2
models 3 days ago
liked a
model 5 days ago
reacted to black-yt's post with š„ 5 days ago
Post
4823
Hey all ā our ResearchClawBench leaderboard just updated š„
We let AI do real science: 40 tasks across 10 disciplines, compared to human papers. Hard example? šļø Glacier mass change ā AI must integrate 233 datasets from 35 teams, 4 methods, reproduce 6542Ā±387 Gt ice loss vs IPCC. No toy problems.
Latest leaderboard (2026-06-09) š:
Agents: š„ Claude Code 21.5 (50 = match human), $5.3; š„ EvoScientist 18.8, $4.1; š„ Codex CLI 18.4, just $2.0
LLMs+Harness: š„ Claude-Opus-4.8 21.1, $4.0; š„ Claude-Opus-4.7 20.7; š„ MiniMax-M3 19.8, only $0.45; Qwen3.7-Max 18.7, $0.42, 11min š„
Claude still king, but MiniMax/Qwen/DeepSeek are crazy cheap and competitive. Expensive isn't always better.
š Code & star: https://github.com/InternScience/ResearchClawBench
š Website: https://internscience.github.io/ResearchClawBench-Home/
š¤ Upvote paper: ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research (2606.07591)
We let AI do real science: 40 tasks across 10 disciplines, compared to human papers. Hard example? šļø Glacier mass change ā AI must integrate 233 datasets from 35 teams, 4 methods, reproduce 6542Ā±387 Gt ice loss vs IPCC. No toy problems.
Latest leaderboard (2026-06-09) š:
Agents: š„ Claude Code 21.5 (50 = match human), $5.3; š„ EvoScientist 18.8, $4.1; š„ Codex CLI 18.4, just $2.0
LLMs+Harness: š„ Claude-Opus-4.8 21.1, $4.0; š„ Claude-Opus-4.7 20.7; š„ MiniMax-M3 19.8, only $0.45; Qwen3.7-Max 18.7, $0.42, 11min š„
Claude still king, but MiniMax/Qwen/DeepSeek are crazy cheap and competitive. Expensive isn't always better.
š Code & star: https://github.com/InternScience/ResearchClawBench
š Website: https://internscience.github.io/ResearchClawBench-Home/
š¤ Upvote paper: ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research (2606.07591)
- 2 replies
liked 3
models 6 days ago
huihui-ai/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated
Any-to-Any ā¢ 12B ā¢ Updated ā¢ 468 ā¢ 17
Vegss/CHADROCK3.6-35B-UNCENSORED-MTP-STRIX-LEAN
Text Generation ā¢ 36B ā¢ Updated ā¢ 207 ā¢ 1
OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-GGUF
Image-Text-to-Text ā¢ 125B ā¢ Updated ā¢ 2k ā¢ 2
liked a
model 10 days ago
liked a
model 11 days ago
reacted to pankajpandey-dev's post with š„ 14 days ago
Post
14969
š®š³ Qwen3-4B Hindi Instruct v2 ā a Hindi LLM that runs on your own machine
Most strong Hindi-capable models are either huge or cloud-only. I wanted one that's small enough to run locally but actually follows instructions in Hindi ā so I fine-tuned Qwen3-4B on 10K Hindi instruction pairs and shipped it with a full GGUF quant ladder.
ā Fine-tune (16-bit): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2
ā GGUF (Q4/Q5/Q8): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2-GGUF
Runs in Ollama, llama.cpp, and LM Studio. The Q4_K_M is just 2.5 GB ā fits comfortably on a laptop, CPU or GPU.
Part of my Hindi LLM Series ā building openly-licensed Indic models for local and edge use. More coming (Gemma next). Feedback welcome š
#Hindi #IndicNLP #GGUF #LocalLLM #Qwen
Most strong Hindi-capable models are either huge or cloud-only. I wanted one that's small enough to run locally but actually follows instructions in Hindi ā so I fine-tuned Qwen3-4B on 10K Hindi instruction pairs and shipped it with a full GGUF quant ladder.
ā Fine-tune (16-bit): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2
ā GGUF (Q4/Q5/Q8): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2-GGUF
Runs in Ollama, llama.cpp, and LM Studio. The Q4_K_M is just 2.5 GB ā fits comfortably on a laptop, CPU or GPU.
Part of my Hindi LLM Series ā building openly-licensed Indic models for local and edge use. More coming (Gemma next). Feedback welcome š
#Hindi #IndicNLP #GGUF #LocalLLM #Qwen
- 4 replies
liked a
model 15 days ago
liked a
model 18 days ago
liked 2
models 20 days ago
liked 2
models 22 days ago
liked a
model 29 days ago
liked a
model about 1 month ago
Couldn't load on 64 GB P14s
2
#1 opened about 1 month ago
by leouon