Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Today on DF: is the RTX 2080 Ti the ultimate "fine wine" GPU? It's a win for balanced hardware, features and memory. Here's how it stacks up against RTX 5060 and others seven years after its launch:

Digital Foundry

184,908 subscribers

28,300 views • 1 year ago •via X (Twitter)

Science & Technology Gaming Education

Anya Rossi• Live Now

Private livecam show

7 Comments

Milton1 year ago

Joke is on everybody else - I'm still using a 980 Ti

RedDeer.Games1 year ago

We can't spill the beans about the release date of Maki: Paw of Fury, but make no mistake, things are happening! 🫘😎 We remind you that the game is coming to #NintendoSwitch and #PC #Steam and you can play the demo on PC, here ⤵️ >>> Have a great day!

Krytopsy1 year ago

To add more context, the RTX 2080 Ti was launched almost 7 years ago.

VamosReal 🇵🇸1 year ago

Base PS5 outperforms the 3080 Ti / 4070 Super, PC builds!

Wokest1 year ago

Isn't this exactly the kind of content that Rich said he would never do?

Dochex1 year ago

Are you going to say people should own an RTX card again in this one? Think of the developers, they can place lights faster! 🤣

m1k331 year ago

Seeing Jensen out of his leather jacket is crazy

Related Videos

The new DF Direct Weekly is available on early access for backers of our Supporter Program, discussing RTX 4060 and 4060 Ti and whether the latest patch fixes Jedi Survivor on PC...

The new DF Direct Weekly is available on early access for backers of our Supporter Program, discussing RTX 4060 and 4060 Ti and whether the latest patch fixes Jedi Survivor on PC...

Digital Foundry

40,235 views • 3 years ago

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth

Marktechpost AI Dev News ⚡

31,551 views • 6 months ago

Coming Soon! In collaboration with MADLAD, QuirkyPlague, and ItsDrCat, we've brought RTX to Better on Bedrock. BetterRTX is required for the best experience since it uses new BetterRTX features. Feel free to check out Better RTX:

Coming Soon! In collaboration with MADLAD, QuirkyPlague, and ItsDrCat, we've brought RTX to Better on Bedrock. BetterRTX is required for the best experience since it uses new BetterRTX features. Feel free to check out Better RTX:

FoxyStar Studios

16,782 views • 1 year ago

#RWBY premiered 11 years ago today at RTX 2013 with quite the iconic fight. And now, RWBY is attending #AnimeExpo2024 after going radio silent for a couple months. Will this be the day we've waited for?

#RWBY premiered 11 years ago today at RTX 2013 with quite the iconic fight. And now, RWBY is attending #AnimeExpo2024 after going radio silent for a couple months. Will this be the day we've waited for?

Robin

82,591 views • 2 years ago

Daniel Owen also tested out Outer Worlds 2 on his RTX 5090 rig with Very High Settings at Native 4k with Hardware RT disabled and look at the framerate... Its honestly shocking how a game that looks like its made for PS4 era runs below 40FPS even on the highest end hardware. Thanks to UE5

Daniel Owen also tested out Outer Worlds 2 on his RTX 5090 rig with Very High Settings at Native 4k with Hardware RT disabled and look at the framerate... Its honestly shocking how a game that looks like its made for PS4 era runs below 40FPS even on the highest end hardware. Thanks to UE5

NikTek

1,062,032 views • 8 months ago

Doom: The Dark Ages on PC delivers an excellent experience - even on mainstream/less than stellar hardware. See how well it runs on a Ryzen 5 3600 and RTX 4060 combo, plus optimised settings for three classes of PC kit:

Doom: The Dark Ages on PC delivers an excellent experience - even on mainstream/less than stellar hardware. See how well it runs on a Ryzen 5 3600 and RTX 4060 combo, plus optimised settings for three classes of PC kit:

Digital Foundry

139,523 views • 1 year ago

CHRISTMAS GIVEAWAY!🎄🎁 Digital Storm and PNY Technologies are teaming up to give you the ultimate gaming upgrade. Win a Digital Storm Corsa with a PNY GeForce RTX 4080 SUPER and unleash DLSS for max quality and max FPS.

CHRISTMAS GIVEAWAY!🎄🎁 Digital Storm and PNY Technologies are teaming up to give you the ultimate gaming upgrade. Win a Digital Storm Corsa with a PNY GeForce RTX 4080 SUPER and unleash DLSS for max quality and max FPS.

Digital Storm

20,816 views • 1 year ago

#Battlefield6 NVIDIA DLSS 4 Reveal Trailer 📽️ The game includes support for DLSS 4 with Multi Frame Generation, DLSS Frame Generation, DLSS Super Resolution, DLAA, and NVIDIA Reflex. Desktop GPUs Performance At 4K, Ultra settings, DLSS 4 with Multi Frame Generation and DLSS Super Resolution multiply Battlefield 6's GeForce RTX 50 Series frame rates by an average of 3.8X. ▪️ GeForce RTX 5090 performance rockets to over 470 FPS. ▪️ GeForce RTX 5080 exceeds 330 FPS. ▪️ GeForce RTX 5070 Ti is in touching distance of 300 FPS. ▪️ GeForce RTX 5070 surpasses 230 FPS. At 2560x1440, Ultra settings, DLSS 4 with Multi Frame Generation and DLSS Super Resolution increase Battlefield 6 frame rates by an average of 3X. ▪️ GeForce RTX 5090 runs at almost 600 FPS. ▪️ GeForce RTX 5060 Ti over 240 FPS. At 1920x1080, Ultra settings, the combination of DLSS 4 with Multi Frame Generation and DLSS Super Resolution boost Battlefield 6’s GeForce RTX 50 Series frame rates by an average of 2.9X. ▪️ Allowing every GPU in NVIDIA's line-up to play at over 230 FPS, maxing out at over 740 FPS on the GeForce RTX 5090. Laptop GPUs Performance GeForce RTX 50 Series Laptop GPUs benefit similarly from DLSS 4 with Multi Frame Generation and DLSS Super Resolution, with Battlefield 6 frame rates multiplied by 3X on average at 2560x1600, with Ultra settings, enabling performance of up to 360 FPS. At 1920x1080, Ultra settings, GeForce RTX 50 Series Laptop GPU performance increases by 2.8X on average, enabling Battlefield 6 frame rates to surpass 480 FPS, and the range to run at over 200 frames per second.

#Battlefield6 NVIDIA DLSS 4 Reveal Trailer 📽️ The game includes support for DLSS 4 with Multi Frame Generation, DLSS Frame Generation, DLSS Super Resolution, DLAA, and NVIDIA Reflex. Desktop GPUs Performance At 4K, Ultra settings, DLSS 4 with Multi Frame Generation and DLSS Super Resolution multiply Battlefield 6's GeForce RTX 50 Series frame rates by an average of 3.8X. ▪️ GeForce RTX 5090 performance rockets to over 470 FPS. ▪️ GeForce RTX 5080 exceeds 330 FPS. ▪️ GeForce RTX 5070 Ti is in touching distance of 300 FPS. ▪️ GeForce RTX 5070 surpasses 230 FPS. At 2560x1440, Ultra settings, DLSS 4 with Multi Frame Generation and DLSS Super Resolution increase Battlefield 6 frame rates by an average of 3X. ▪️ GeForce RTX 5090 runs at almost 600 FPS. ▪️ GeForce RTX 5060 Ti over 240 FPS. At 1920x1080, Ultra settings, the combination of DLSS 4 with Multi Frame Generation and DLSS Super Resolution boost Battlefield 6’s GeForce RTX 50 Series frame rates by an average of 2.9X. ▪️ Allowing every GPU in NVIDIA's line-up to play at over 230 FPS, maxing out at over 740 FPS on the GeForce RTX 5090. Laptop GPUs Performance GeForce RTX 50 Series Laptop GPUs benefit similarly from DLSS 4 with Multi Frame Generation and DLSS Super Resolution, with Battlefield 6 frame rates multiplied by 3X on average at 2560x1600, with Ultra settings, enabling performance of up to 360 FPS. At 1920x1080, Ultra settings, GeForce RTX 50 Series Laptop GPU performance increases by 2.8X on average, enabling Battlefield 6 frame rates to surpass 480 FPS, and the range to run at over 200 frames per second.

Battlefield Bulletin

30,559 views • 9 months ago

First hands-on with Microsoft’s new Surface Laptop Ultra. Microsoft is clearly positioning this as a new class of creator and AI laptop, powered by new NVIDIA silicon with an RTX GPU built for local AI, creative workflows, and gaming. A few standout specs: -New NVIDIA chip with RTX GPU -Up to 1 petaflop of AI compute -Up to 128GB unified memory -15-inch mini-LED PixelSense Ultra touchscreen -3:2 aspect ratio -262 PPI -Up to 2,000 nits peak HDR brightness -Less than 18mm thick

First hands-on with Microsoft’s new Surface Laptop Ultra. Microsoft is clearly positioning this as a new class of creator and AI laptop, powered by new NVIDIA silicon with an RTX GPU built for local AI, creative workflows, and gaming. A few standout specs: -New NVIDIA chip with RTX GPU -Up to 1 petaflop of AI compute -Up to 128GB unified memory -15-inch mini-LED PixelSense Ultra touchscreen -3:2 aspect ratio -262 PPI -Up to 2,000 nits peak HDR brightness -Less than 18mm thick

Chubby♨️

65,993 views • 1 month ago

Today on DF, after a poor Nintendo Direct debut, the great news is that Fallout Anniversary Edition on Switch 2 is impressive - with 30fps, 40fps and target 60fps options. Here's how it looks, along with the requisite console comparisons:

Today on DF, after a poor Nintendo Direct debut, the great news is that Fallout Anniversary Edition on Switch 2 is impressive - with 30fps, 40fps and target 60fps options. Here's how it looks, along with the requisite console comparisons:

Digital Foundry

110,815 views • 4 months ago

I tried Motorstorm on RPCS3 and can confirm it is playable. However, terrain deformation is extremely taxing on the GPU so I can't have 60 FPS at 1440p on my RTX 3070. You will have to either drop the resolution or lock the framerate to its original 30 FPS cap.

I tried Motorstorm on RPCS3 and can confirm it is playable. However, terrain deformation is extremely taxing on the GPU so I can't have 60 FPS at 1440p on my RTX 3070. You will have to either drop the resolution or lock the framerate to its original 30 FPS cap.

Dream's Longest Day

134,686 views • 7 months ago

💥 The future of digital payments is being shaped by three major players: $XRP, $XLM, and $RTX. ⚫ XRP brings banks into blockchain. Fast, reliable settlement for institutions that still run the old system. 🔵 XLM empowers NGOs and financial inclusion. It helps connect the unbanked and underserved to the global economy. 🟡 RTX puts the power in people’s hands. No banks. No middlemen. Just pure peer-to-peer payments with real merchant adoption. 🚨 Market reality: • XRP = $30B+ • XLM = $3B • RTX = < $100M Each project has its mission. Each is strong in its lane. But RTX stands out as the one designed for everyday users. 💣 No borders. No permissions. No gatekeepers. 🛡️ Just fast, decentralized, and user-owned payments. That’s $RTX. Visit 🔗 Today. Warm Regards, Remittix Team

💥 The future of digital payments is being shaped by three major players: $XRP, $XLM, and $RTX. ⚫ XRP brings banks into blockchain. Fast, reliable settlement for institutions that still run the old system. 🔵 XLM empowers NGOs and financial inclusion. It helps connect the unbanked and underserved to the global economy. 🟡 RTX puts the power in people’s hands. No banks. No middlemen. Just pure peer-to-peer payments with real merchant adoption. 🚨 Market reality: • XRP = $30B+ • XLM = $3B • RTX = < $100M Each project has its mission. Each is strong in its lane. But RTX stands out as the one designed for everyday users. 💣 No borders. No permissions. No gatekeepers. 🛡️ Just fast, decentralized, and user-owned payments. That’s $RTX. Visit 🔗 Today. Warm Regards, Remittix Team

Remittix

23,191 views • 10 months ago

Nvidia announces the new RTX Spark, a new platform powered by the NX1 CPU, and shows off Spark laptops running 007 First Light and Forza 6. The CPU has 20 ARM based cores and a Blackwell RTX GPU with 6144 CUDA Cores. This is the same core count as a 5070, but with 128GB of unified LPDDR5X RAM memory sitting in the same package as the CPU and GPU. The entire Nvidia software stack is available, particularly CUDA, vital for AI. Nvidia's new laptops will likely be ideal for running local LLMs be cause the unified memory means you can load models up to 120-180B parameters (quantized). These laptops are expected to ship later this year and could become strong competitors to high-end MacBooks and even Mac Studios for local AI workloads, thanks to CUDA support and unified memory. Price is unannounced.

Nvidia announces the new RTX Spark, a new platform powered by the NX1 CPU, and shows off Spark laptops running 007 First Light and Forza 6. The CPU has 20 ARM based cores and a Blackwell RTX GPU with 6144 CUDA Cores. This is the same core count as a 5070, but with 128GB of unified LPDDR5X RAM memory sitting in the same package as the CPU and GPU. The entire Nvidia software stack is available, particularly CUDA, vital for AI. Nvidia's new laptops will likely be ideal for running local LLMs be cause the unified memory means you can load models up to 120-180B parameters (quantized). These laptops are expected to ship later this year and could become strong competitors to high-end MacBooks and even Mac Studios for local AI workloads, thanks to CUDA support and unified memory. Price is unannounced.

Grummz

30,573 views • 1 month ago

six months ago this wasn't happening on 8gb vram. running unsloth's Q4_K_XL quant of gemma 4 26b-a4b-it-qat, a sparse MoE model with only 4b active params on a single rtx 4060 laptop gpu, 8gb vram, 20+ tok/s decode. no cloud, no api, no offload hacks. just a gaming laptop on battery. what makes it fit: google's QAT (quantization aware training), plus MTP (multi token prediction) support in the latest llama.cpp builds. that combo is the single biggest unlock for local inference on low vram. rtx 3060, rtx 3070, gtx 1070, gtx 1080, rtx 4050, rtx 4060, rtx 5050, rtx 5060 — any 6-8gb consumer gpu, old or new — this model runs on it. world cup season, so i told it to build a soccer themed flappy bird clone. one shot, zero iteration, fully playable. six months ago an 8gb model could barely clone vanilla flappy bird. now it's shipping a themed game from a sparse MoE model running locally on a laptop battery. inference benchmarks: - decode throughput: 30 tok/s - context: 64k. this is the real unlock. 64k ctx is what makes a hermes agent loop viable locally on this model, not just single-turn chat. llama.cpp flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 -cmoe --port 8080 game's deployed on my own site, built and shipped end to end with open source llm, zero closed source api dependency in the pipeline. link in the description. gguf weights on huggingface, link in the comments. pull it down, run it on whatever 8gb card is sitting in your rig. try the game and tell me your score and what you want in v2. local llms on consumer gpus stopped being a meme.

six months ago this wasn't happening on 8gb vram. running unsloth's Q4_K_XL quant of gemma 4 26b-a4b-it-qat, a sparse MoE model with only 4b active params on a single rtx 4060 laptop gpu, 8gb vram, 20+ tok/s decode. no cloud, no api, no offload hacks. just a gaming laptop on battery. what makes it fit: google's QAT (quantization aware training), plus MTP (multi token prediction) support in the latest llama.cpp builds. that combo is the single biggest unlock for local inference on low vram. rtx 3060, rtx 3070, gtx 1070, gtx 1080, rtx 4050, rtx 4060, rtx 5050, rtx 5060 — any 6-8gb consumer gpu, old or new — this model runs on it. world cup season, so i told it to build a soccer themed flappy bird clone. one shot, zero iteration, fully playable. six months ago an 8gb model could barely clone vanilla flappy bird. now it's shipping a themed game from a sparse MoE model running locally on a laptop battery. inference benchmarks: - decode throughput: 30 tok/s - context: 64k. this is the real unlock. 64k ctx is what makes a hermes agent loop viable locally on this model, not just single-turn chat. llama.cpp flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 -cmoe --port 8080 game's deployed on my own site, built and shipped end to end with open source llm, zero closed source api dependency in the pipeline. link in the description. gguf weights on huggingface, link in the comments. pull it down, run it on whatever 8gb card is sitting in your rig. try the game and tell me your score and what you want in v2. local llms on consumer gpus stopped being a meme.

Alok

60,725 views • 24 days ago

PowerInfer - a high-speed inference engine for deploying LLMs locally. Just came across this super interesting project on speeding up inference. It's not MoE but it's a simple approach that exploits the high locality in LLM inference to design a GPU-CPU hybrid inference engine. Hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons (the majority) are computed on the CPU. This approach significantly reduces GPU memory demands and CPU-GPU data transfer. It achieves an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs on a single NVIDIA RTX 4090 GPU. It's on only 18% lower than that achieved by a top-tier server-grade A100 GPU. It also significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy. There is a lot more innovation around inference that's coming fast. Really encouraged by the study on sparse computation to enhance the computational efficiency of LLMs. It's now possible to use PowerInfer with Llama 2 and Faclon 40B. Mistral-7B support is coming soon!

PowerInfer - a high-speed inference engine for deploying LLMs locally. Just came across this super interesting project on speeding up inference. It's not MoE but it's a simple approach that exploits the high locality in LLM inference to design a GPU-CPU hybrid inference engine. Hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons (the majority) are computed on the CPU. This approach significantly reduces GPU memory demands and CPU-GPU data transfer. It achieves an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs on a single NVIDIA RTX 4090 GPU. It's on only 18% lower than that achieved by a top-tier server-grade A100 GPU. It also significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy. There is a lot more innovation around inference that's coming fast. Really encouraged by the study on sparse computation to enhance the computational efficiency of LLMs. It's now possible to use PowerInfer with Llama 2 and Faclon 40B. Mistral-7B support is coming soon!

elvis

261,622 views • 2 years ago

The ticker is $CHIP. It sets the interest rate of artificial intelligence. Today we're announcing the Foundation and its governance token, built on over $7.7 billion in trading volume and real revenue from GPU-backed lending. Here's how we got here...

The ticker is $CHIP. It sets the interest rate of artificial intelligence. Today we're announcing the Foundation and its governance token, built on over $7.7 billion in trading volume and real revenue from GPU-backed lending. Here's how we got here...

USD.AI

340,795 views • 5 months ago

a new 8GB VRAM GPU dense Local LLM leader was born yesterday runs on: RTX 4060 / RTX 3070 / RTX 2080. any 8GB card Qwen 3.5 9B (dense) was the go to for 6-8GB VRAM builds. Gemma 4 12B QAT (dense) just changed that. same llama.cpp + cuda 13.2. i7 12700H. 16GB RAM. same -ngl 99 flags. same 48k context. unsloth gemma-4-12b-it-Q4_K_M.gguf → 15 tok/sec @ 48k ctx unsloth gemma-4-12B-it-qat-UD-Q4_K_XL.gguf → 32 tok/sec @ 48k ctx → 26 tok/sec @ 64k ctx 64k context is a big deal. Hermes 3 agent requires 64k minimum to run. you're now getting full hermes compatible context on a budget consumer GPU at 26 tok/sec locally. 2.1x faster on identical hardware. and here's the part that breaks your brain: the QAT-UD-Q4_K_XL is actually SMALLER than the Q4_K_M "XL" why? QAT = Quantization Aware Training Google didn't train the model first and compress it later they trained it to be quantized from day one the weights already know how to survive low precision that's why you get more quality per byte llamacpp flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf -cnv -ngl 99 -c 48000 -v fits in 8GB VRAM clean. no API. no cloud. no subscription. and this isn't even the MTP variant yet Gemma-4-E2B QAT runs on 3GB RAM, E4B on 5GB, 12B on 7GB, 26-A4B on 15GB and 31B on 18GB. I have benchmarked the 26b and 31b qat as well on a single RTX 4090, checkout the comments for details. If you have a 6GB or 8GB VRAM GPU, post your numbers. more benchmarks and configs coming soon

a new 8GB VRAM GPU dense Local LLM leader was born yesterday runs on: RTX 4060 / RTX 3070 / RTX 2080. any 8GB card Qwen 3.5 9B (dense) was the go to for 6-8GB VRAM builds. Gemma 4 12B QAT (dense) just changed that. same llama.cpp + cuda 13.2. i7 12700H. 16GB RAM. same -ngl 99 flags. same 48k context. unsloth gemma-4-12b-it-Q4_K_M.gguf → 15 tok/sec @ 48k ctx unsloth gemma-4-12B-it-qat-UD-Q4_K_XL.gguf → 32 tok/sec @ 48k ctx → 26 tok/sec @ 64k ctx 64k context is a big deal. Hermes 3 agent requires 64k minimum to run. you're now getting full hermes compatible context on a budget consumer GPU at 26 tok/sec locally. 2.1x faster on identical hardware. and here's the part that breaks your brain: the QAT-UD-Q4_K_XL is actually SMALLER than the Q4_K_M "XL" why? QAT = Quantization Aware Training Google didn't train the model first and compress it later they trained it to be quantized from day one the weights already know how to survive low precision that's why you get more quality per byte llamacpp flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf -cnv -ngl 99 -c 48000 -v fits in 8GB VRAM clean. no API. no cloud. no subscription. and this isn't even the MTP variant yet Gemma-4-E2B QAT runs on 3GB RAM, E4B on 5GB, 12B on 7GB, 26-A4B on 15GB and 31B on 18GB. I have benchmarked the 26b and 31b qat as well on a single RTX 4090, checkout the comments for details. If you have a 6GB or 8GB VRAM GPU, post your numbers. more benchmarks and configs coming soon

Alok

259,993 views • 1 month ago