Research directly related to Chess technology.
Ben Kelly PRO
YellowjacketGames
AI & ML interests
None yet
Recent Activity
updated
a collection
about 3 hours ago
[papers] Gameplay Optimization
replied to
danielhanchen's
post
about 13 hours ago
You can now run Kimi K2.5 locally! 🔥
We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.
GGUF: https://huggingface.co/unsloth/Kimi-K2.5-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k2.5
replied to
danielhanchen's
post
about 14 hours ago
You can now run Kimi K2.5 locally! 🔥
We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.
GGUF: https://huggingface.co/unsloth/Kimi-K2.5-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k2.5
Organizations
Models that run well on a *standalone* RTX a6000's 48gb of VRAM.
-
unsloth/Qwen-Image-Edit-2511-GGUF
Image-to-Image • 20B • Updated • 139k • 327 -
unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF
24B • Updated • 157k • 90 -
zai-org/GLM-Image
Text-to-Image • Updated • 14.4k • • 1.01k -
nvidia/personaplex-7b-v1
Audio-to-Audio • Updated • 54.5k • 1.51k
TPS can be as low as 1.0, seriously. its SLOW.
-
unsloth/GLM-4.7-GGUF
Text Generation • 358B • Updated • 113k • 190 -
unsloth/DeepSeek-R1-0528-GGUF
Text Generation • 671B • Updated • 3.64k • 193 -
unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF
Image-to-Text • 401B • Updated • 4.98k • 43 -
unsloth/MiniMax-M2.1-GGUF
Text Generation • 229B • Updated • 129k • 165
hey, you gotta try. any precision acceptable here, QA check the actual result quality. at your own risk, fool.
-
nvidia/Nemotron-Orchestrator-8B
Text Generation • 8B • Updated • 18.4k • 538 -
allenai/SERA-8B-GA
8B • Updated • 9 • 9 -
GAIR/daVinci-Dev-72B
Text Generation • 73B • Updated • 105 • 5 -
A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
Paper • 2601.13288 • Published • 12
-
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
Paper • 2601.14249 • Published • 9 -
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
Paper • 2402.07033 • Published • 19 -
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences
Paper • 2601.07251 • Published • 11 -
GameTalk: Training LLMs for Strategic Conversation
Paper • 2601.16276 • Published • 12
Seriously, look at the size of these dumps! They're a huge pile of data, dumped on your doorstep!
Research papers that may contribute to a broader approach to teaching machines how to play complex strategy games beyond just Chess.
-
OptiMind: Teaching LLMs to Think Like Optimization Experts
Paper • 2509.22979 • Published • 3 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 51 -
Zero-Overhead Introspection for Adaptive Test-Time Compute
Paper • 2512.01457 • Published • 1 -
Confidence Estimation for LLMs in Multi-turn Interactions
Paper • 2601.02179 • Published • 16
The best little card under 100 euros. Full Precision vs Quants not benchmarked. This card is so much better at running inference than you realize.
-
MaziyarPanahi/Nemotron-Orchestrator-8B-GGUF
Text Generation • 8B • Updated • 71.2k • 4 -
unsloth/Qwen3-4B-Instruct-2507-GGUF
4B • Updated • 59k • 136 -
unsloth/SmolLM3-3B-128K-GGUF
3B • Updated • 2.82k • 37 -
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation • 8B • Updated • 50.4k • 367
Toaster Tier but not iGPU
Emphasis on Portuguese, Spanish, Vietnamese, Hebrew
The stuff we actually use, pruned on an ongoing basis.
-
black-forest-labs/FLUX.2-dev
Image-to-Image • Updated • 133k • • 1.3k -
unsloth/Qwen-Image-Edit-2511-GGUF
Image-to-Image • 20B • Updated • 139k • 327 -
zai-org/GLM-Image
Text-to-Image • Updated • 14.4k • • 1.01k -
fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA
Image-to-Image • Updated • 80.3k • • 890
-
UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation
Paper • 2504.08761 • Published • 7 -
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling
Paper • 2512.23959 • Published • 111 -
DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal
Paper • 2601.18081 • Published • 7
Research directly related to Chess technology.
Research papers that may contribute to a broader approach to teaching machines how to play complex strategy games beyond just Chess.
-
OptiMind: Teaching LLMs to Think Like Optimization Experts
Paper • 2509.22979 • Published • 3 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 51 -
Zero-Overhead Introspection for Adaptive Test-Time Compute
Paper • 2512.01457 • Published • 1 -
Confidence Estimation for LLMs in Multi-turn Interactions
Paper • 2601.02179 • Published • 16
Models that run well on a *standalone* RTX a6000's 48gb of VRAM.
-
unsloth/Qwen-Image-Edit-2511-GGUF
Image-to-Image • 20B • Updated • 139k • 327 -
unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF
24B • Updated • 157k • 90 -
zai-org/GLM-Image
Text-to-Image • Updated • 14.4k • • 1.01k -
nvidia/personaplex-7b-v1
Audio-to-Audio • Updated • 54.5k • 1.51k
The best little card under 100 euros. Full Precision vs Quants not benchmarked. This card is so much better at running inference than you realize.
-
MaziyarPanahi/Nemotron-Orchestrator-8B-GGUF
Text Generation • 8B • Updated • 71.2k • 4 -
unsloth/Qwen3-4B-Instruct-2507-GGUF
4B • Updated • 59k • 136 -
unsloth/SmolLM3-3B-128K-GGUF
3B • Updated • 2.82k • 37 -
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation • 8B • Updated • 50.4k • 367
TPS can be as low as 1.0, seriously. its SLOW.
-
unsloth/GLM-4.7-GGUF
Text Generation • 358B • Updated • 113k • 190 -
unsloth/DeepSeek-R1-0528-GGUF
Text Generation • 671B • Updated • 3.64k • 193 -
unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF
Image-to-Text • 401B • Updated • 4.98k • 43 -
unsloth/MiniMax-M2.1-GGUF
Text Generation • 229B • Updated • 129k • 165
Toaster Tier but not iGPU
hey, you gotta try. any precision acceptable here, QA check the actual result quality. at your own risk, fool.
Emphasis on Portuguese, Spanish, Vietnamese, Hebrew
-
nvidia/Nemotron-Orchestrator-8B
Text Generation • 8B • Updated • 18.4k • 538 -
allenai/SERA-8B-GA
8B • Updated • 9 • 9 -
GAIR/daVinci-Dev-72B
Text Generation • 73B • Updated • 105 • 5 -
A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
Paper • 2601.13288 • Published • 12
The stuff we actually use, pruned on an ongoing basis.
-
black-forest-labs/FLUX.2-dev
Image-to-Image • Updated • 133k • • 1.3k -
unsloth/Qwen-Image-Edit-2511-GGUF
Image-to-Image • 20B • Updated • 139k • 327 -
zai-org/GLM-Image
Text-to-Image • Updated • 14.4k • • 1.01k -
fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA
Image-to-Image • Updated • 80.3k • • 890
-
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
Paper • 2601.14249 • Published • 9 -
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
Paper • 2402.07033 • Published • 19 -
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences
Paper • 2601.07251 • Published • 11 -
GameTalk: Training LLMs for Strategic Conversation
Paper • 2601.16276 • Published • 12
-
UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation
Paper • 2504.08761 • Published • 7 -
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling
Paper • 2512.23959 • Published • 111 -
DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal
Paper • 2601.18081 • Published • 7
Seriously, look at the size of these dumps! They're a huge pile of data, dumped on your doorstep!