GeForce RTX 4070

For what it's worth, I tend to upgrade my wife and I's laptops every 1-2 years, usually during Black Friday sales. Two years ago, I snagged laptops with a 32GB RAM, RTX 4070, and i9-13900HX for $1,500. Historically I've been able to get a sizeable bump in CPU + GPU performance for around the same price point, but currently there's nothing on the market. It feels like the pace of development has slowed in the last few years. I don't think I'll be upgrading again until consumer X3D CPU laptops become available for a non-egregious price.

[...] It runs fine on CPU-- on a 14700KF gets 40tg/s and 250pp/s and on a ordinary gpu (RTX 4070) does over 200tg/s with no MTP and 7185pp/s. (my figures are Q8, though presumably a good Q4 would be faster) It's certainly not as capable as something that needs a high memory gpu for quick performance, but I was quite impressed with it for what it is. [...]

[...] A midrange gaming desktop from mid 2023, something like rtx 4070 and ryzen 7800x3d, can still play pretty much any video game on max settings and high framerate at 1440p, and has sufficient performance for most workstation-esque tasks as long as you have enough ram. Similarly, the only thing my spare macbook m2 lacks compared to m5 is hardware av1 decoding - the performance is worse, but I don't really notice it in normal usage, and macOS 27 runs perfectly well on it. [...] So, fingers crossed nothing breaks down and that some of the funny money goes into R&D which will eventually trickle down to consumer devices in a few years (16TB gum stick SSDs at sane prices pretty please) instead of endless datacenter GPUs and SSDs that will be tossed into a shredder in x years.

The previous documented record for simultaneous Claude Code agents is 16, set by Anthropic's own engineering team building a C compiler. [...] What made this possible: I built a Tokio-native LLM orchestration pipeline in Rust that routes inference through a local Mistral 7B model running on an RTX 4070. [...]

[...] I also have a MSI katana laptop with RTX 4070 and that had been a disaster. [...] I don't play any games but Bazzite took my MSI laptop from feeling like a waste of money to absolutely awesome.

[...] Ryzen 5950x, 64GB RAM, RTX 4070, AMD 6500XT. [...] For example, if I lose access to the hypervisor over the network, getting the system back online can be a bit of a PITA as you can no longer just plug it into a screen to update any static network configuration. My current solution to this is enabling DHCP on Proxmox and managing the IP with static mappings at the router level. [...]

In my opinion, if you have the money, a Razer or Asus laptop is the highest quality machine that you can get to run Linux. [...] Large trackpad, 16:10, 6 hours of battery life (pretty good for linux) and an RTX 4070. That said, it is absurdly expensive.

Obvious massive asterisk that benchmarks are not always realworld use: Apple M5, Single core Geekbench: 4,200 ( Apple M5 Pro (15-core, lower core version), multicore: 26,000 ( compare this to the top of the line Intel Panther Lake chips, which have comparable battery life. I cherry picked a 16" Dell XPS machine, which has the best thermal headroom, for its best score: Single core: 2,900 Multicore (16-cores): 16,900 Geekbench is bursty, so we can look at more sustained test, Cinebench 2024: Single core: XPS 16 (2026): 111 MacBook Pro 16 (M5, 2026): 203 Multicore: XPS 16 (2026): 613 MacBook Pro 16 (M5, 2026): 2065 on GPU, "Despite the XPS 16's discrete Nvidia RTX 4070 laptop GPU, the MacBook Pro M4 Pro's unified memory architecture outpaced the Dell in 4K video export and machine learning inference benchmarks by 22 percent on average." For GPU, this is not comprehensive. [...] Until last week, prices on Framework/Dell vs. [...] I think Apple is probably 10-20% expesnive at this point, but adjusting for performance, Apple still comes out ahead. Apple's displays used to have a huge advantage. Now that you can get OLED displays on performant, efficient Panther Lake machines, this is far less of an Apple advantage. The upshot is that the new Panther Lake machines caught up considerably to Apple, but they're still about 20-30% slower

[...] You can't just add a dedicated GPU to a cheap miniPC with an integrated graphics- power delivery and airflow will have to be different, and you may be surprised to find out that even the cheapest mini PCs with dedicated graphics aren't significantly cheaper than a Steam machine (if at all). And then my personal experience with these cheap no-brand mini-computers is that their Linux compatibility is spotty, BIOS updates are non-existend, quality control is severely lacking, and you have basically no support. They are also often pretty loud, overheat and die within a year or two. [...] The problem is once the price crosses a thousand, I'd rather add, say, 500 eur, and get a much more powerful machine. I see a point for the cheapest bottom of the barrel gaming pc/handheld (which would be 700-750) with many performance tradeoffs, but this doesn't look like a good enough upgrade from that. A 12+ GB RTX4070-class videocard, 24-32GB of RAM and maybe even an 8-core CPU for $1500+ would likely be more usable in the current market

Last year I read a lot of reviews making a fuss about the RTX 4070 (mobile) having "only" 8GB VRAM but it's what I ended up buying and it just hasn't been an issue where I'm like, shoot my games aren't fast enough or pretty enough to have fun. Sometimes I think number-based reviews miss the point, and I miss HardOCP!

I've been on the same PSU for I think 13 years now, its currently running my Ryzen 7 3700x and RTX4070 desktop. I suppose if its not a great quality PSU or its already suspected of causing issues then replacing is a good idea.

Been working on a similar project for doing animal behavioral analysis on cameras setup in a barn. I got YOLO running in real-time on several streams on a RTX4070. [...]

[...] Using an RTX 4070. [...]

I have tried everything (that will run on a 12GB RTX 4070) and I have yet to find anything with better accuracy than Whisper V2 Large for my dataset (discord audio from TTRPG sessions, isolated per-speaker, mostly non-American accents)

[...] I run bazzite-DX (nvidia rtx4070) for dev and pleasure and gaming there is ON POINT. [...]

[...] I have an RTX 4070 gaming PC and an M4 MacBook Pro w/ 36GB shared memory. When models fit in VRAM, the RTX 4070 still runs much faster. [...]

[...] That was until I got a 4k monitor at work and experienced 4k HDR gaming. I immediately went out and bought an RTX 4070 and a 4k monitor and I will never be going back. [...]

I recently bought a Lenovo Legion with RTX4070 I still haven't managed to get Nvidia it working under Linux (the moment I open a browser or anything that uses the GPU extensively things go bad) Disclaimer I am not very familiar with Linux for Desktop - but to me this is an indication that we are not yet in the "just works" state for desktop linux.

[...] Something a bit more practical like an RTX 4070 (with 12GB vram) is about $550. That is bullshit expensive. [...] Better yet just go and buy a console or game on my phone.

From what I understand, NVidia used to have poor Linux support, but apparently that's been fixed. In any case, I haven't run into any serious issues with my RTX 4070.

ASUS - ROG Zephyrus M16 16" 240Hz Gaming Laptop runs Ubuntu 22.04 very well in my opinion: CUDA, Vulkan, Wifi, bluetooth, sleep etc. I installed Linux on a second SSD next to Windows on the original SSD. The version with NVIDIA RTX 4070 costs 1700 USD at Best Buy (the one with RTX 4090 may exceed your budget)

I bought an ASUS gaming laptop, and it's done me fine. Nvidia Geforce RTX 4070 laptop GPU.

Yeah! I got the ROG Zephyrus G14 2024 edition. There's multiple versions, I think the MSRP for the one I have is $2000 USD but I'm not sure how the currency conversion looks since you're based outside the US D: CPU: AMD Ryzen 9 8945HS w/ Radeon 780M Graphics GPU: NVIDIA GeForce RTX 4070 Laptop GPU

Can you list some useful things you can do with such models which are beyond 'fancy' use, like image generation, or standard chat (which is subpar compared to frontier)? I use my RTX4070 (12VRAM/64RAM) mostly for STT, though I am having real trouble to set up working environment for any Whisper derivatives after migrating to Fedora.

With llama.cpp, Intel i9-13900KS CPU, 96 GB RAM, RTX 4070 running locally. The models I'm using right now with that are: gpt-oss-120b-F16.gguf QwenQwen3.5-27B-Q4KM.gguf Qwen3.6-35B-A3B-UD-Q5KXL.gguf gemma-4-31B-it-UD-Q6KXL.gguf

Got a similar result (my RTX 4070 only has 12 GB). I'm curious about whether 24/32 GB meaningfully improves this enough to make it useful.

care to elaborate? i have rtx 4070 12gb vram + 64gb ram, i wonder what models I can run with it. Anything useful?

For people without a 24GB RAM video card, I've got an 8GB RAM one running What're you using for this? llama.cpp? Have a 12GB card (rtx 4070) i'd like to try it on.

I was thinking of trying this on my Windows machine with an RTX 4070 but it sounds like the GPU isn't used in WSL. Was your testing really slow when using just the CPU?