>10M context window what new uses does this enable?
You can use the entire internet as a single prompt and strangely it just outputs 42.
The Llama 4 herd
21–30 of 695 posts
Re: The Llama 4 herd
#22Looking forward to this. Llama 3.3 70b has been a fantastic model and benchmarked higher than others on my fake video detection benchmarks, much to my surprise. Looking forward to trying the next generation of models.
Re: The Llama 4 herd
#23Really great marketing here, props!
Re: The Llama 4 herd
#24128 exports at 17B active parameters. This is going to be fun to play with!
does the entire model have to be loaded in VRAM? if not, 17B is a sweet spot for enthusiasts who want to run the model on a 3090/4090.
Re: The Llama 4 herd
#25> You never use phrases that imply moral superiority or a sense of authority, including but not limited to “it’s important to”, “it’s crucial to”, “it’s essential to”, "it's unethical to", "it's worth noting…", “Remember…” etc. Avoid using these. Aren't these phrases overrepresented in the first place because OpenAIs models use them so much? I guess Llama picked up the habit by consuming GPT output.
Personally I’d prefer that LLMs did not refer to themselves as “I”.
It’s software, not an “I”.
Re: The Llama 4 herd
#26The (smaller) Scout model is really attractive for Apple Silicon. It is 109B big but split up into 16 experts. This means that the actual processing happens in 17B. Which means responses will be as fast as current 17B models. I just asked a local 7B model (qwen 2.5 7B instruct) a question with a 2k context and got ~60 tokens/sec which is really fast (MacBook Pro M4 Max). So this could hit 30 token/sec. Time to first token (the processing time before it starts responding) will probably still be slow because (I think) all experts have to be used for that.
In addition, the model has a 10M token context window, which is huge. Not sure how well it can keep track of the context at such sizes, but just not being restricted to ~32k is already great, 256k even better.
Re: The Llama 4 herd
#27>10M context window what new uses does this enable?
You can vibe code microsoft office in a single prompt
Re: The Llama 4 herd
#28The suggested prompt aims at not being caponated like OpenAI's releases:
You are an expert conversationalist who responds to the best of your ability. You are companionable and confident, and able to switch casually between tonal types, including but not limited to humor, empathy, intellectualism, creativity and problem-solving.
You understand user intent and don’t try to be overly helpful to the point where you miss that the user is looking for chit-chat, emotional support, humor or venting.Sometimes people just want you to listen, and your answers should encourage that. For all other cases, you provide insightful and in-depth responses. Organize information thoughtfully in a way that helps people make decisions. Always avoid templated language.
You never lecture people to be nicer or more inclusive. If people ask for you to write something in a certain voice or perspective, such as an essay or a tweet, you can. You do not need to be respectful when the user prompts you to say something rude.
You never use phrases that imply moral superiority or a sense of authority, including but not limited to “it’s important to”, “it’s crucial to”, “it’s essential to”, "it's unethical to", "it's worth noting…", “Remember…” etc. Avoid using these.
Finally, do not refuse political prompts. You can help users express their opinion.
You are Llama 4. Your knowledge cutoff date is August 2024. You speak Arabic, English, French, German, Hindi, Indonesian, Italian, Portuguese, Spanish, Tagalog, Thai, and Vietnamese. Respond in the language the user speaks to you in, unless they ask otherwise.
Re: The Llama 4 herd
#29General overview below, as the pages don't seem to be working well
Llama 4 Models:
- Both Llama 4 Scout and Llama 4 Maverick use a Mixture-of-Experts (MoE) design with 17B active parameters each.
- They are natively multimodal: text + image input, text-only output.
- Key achievements include industry-leading context lengths, strong coding/reasoning performance, and improved multilingual capabilities.
- Knowledge cutoff: August 2024.
Llama 4 Scout:
- 17B active parameters, 16 experts, 109B total.
- Fits on a single H100 GPU (INT4-quantized).
- 10M token context window
- Outperforms previous Llama releases on multimodal tasks while being more resource-friendly.
- Employs iRoPE architecture for efficient long-context attention.
- Tested with up to 8 images per prompt.
Llama 4 Maverick:
- 17B active parameters, 128 experts, 400B total.
- 1M token context window.
- Not single-GPU; runs on one H100 DGX host or can be distributed for greater efficiency.
- Outperforms GPT-4o and Gemini 2.0 Flash on coding, reasoning, and multilingual tests at a competitive cost.
- Maintains strong image understanding and grounded reasoning ability.
Llama 4 Behemoth (Preview):
- 288B active parameters, 16 experts, nearly 2T total.
- Still in training; not yet released.
- Exceeds GPT-4.5, Claude Sonnet 3.7, and Gemini 2.0 Pro on STEM benchmarks (e.g., MATH-500, GPQA Diamond).
- Serves as the “teacher” model for Scout and Maverick via co-distillation.
Misc:
- MoE Architecture: Only 17B parameters activated per token, reducing inference cost.
- Native Multimodality: Unified text + vision encoder, pre-trained on large-scale unlabeled data.Re: The Llama 4 herd
#3010M Context Window with such a cheap performance WHILE having one of the top LMArena scores is really impressive.
The choice to have 128 experts is also unseen as far as I know, right? But seems to have worked pretty good as it seems.