If it's intelligence + speed you want, nothing comes close to GPT-OSS-120B on Cerebras or Groq.
However, this looks like it has great potential for cost-effectiveness. As of today it's free to use over API on OpenRouter, so a bit unclear what it'll cost when it's not free, but free is free!
I don’t do ‘evals’, but I do process billions of tokens every month, and I’ve found these small Nvidia models to be the best by far for their size currently.
As someone else mentioned, the GPT-OSS models are also quite good (though I haven’t found how to make them great yet, though I think they might age well like the Llama 3 models did and get better with time!).
But for a defined task, I’ve found task compliance, understanding, and tool call success rates to be some of the highest on these Nvidia models.
For example, I have a continuous job that evaluates if the data for a startup company on aVenture.vc could have overlapping/conflated two similar but unrelated companies for news articles, research details, investment rounds, etc… which is a token hungry ETL task! And I recently retested this workflow on the top 15 or so models today with <125b parameters, and the Nvidia models were among the best performing for this type of work, particularly around non-hallucination if given adequate grounding.
Also, re: cost - I run local inference on several machines that run continuously, in addition to routing through OpenRouter and the frontier providers, and was pleasantly surprised to find that if I’m a paying customer of OpenRouter otherwise, the free variant there from Nvidia is quite generous for limits, too.
Yes, I run it locally on 3 different AMD Strix Halo machines (Framework Desktop and 2 GMKTec machines, 128gb x 2, 96gb x 1) and a Mac Studio M2 Ultra 128gb of unified memory.
I’ve used several runtimes, including vLLM. Works great! Speedy. Best results with Ubuntu after trying a few different distributions and Vulkan and ROCm drivers.
I recently pitted gpt-oss 120b against Qwen3-Next 80b on a lot of internal benchmarks (for production use), and for me, gpt-oss was slightly slower (vLLM, both fit in VRAM), much worse at multilingual tasks (33 languages evaluated), and had worse instruction following (e.g., Qwen3-Next was able to reuse the same prompts I used for Gemma3 perfectly, while gpt-oss struggled and RAG benchmarks suddenly went from 90% to 60% without additional prompt engineering).
And that's with Qwen3-Next being a random unofficial 4-bit quant (compared to gpt-oss having native support) + I had to disable multi-token prediction in Qwen3-Next because vLLM crashed with it.
Has someone here tried both gpt-oss 120b and Qwen3-Next 80b? Maybe I was doing something wrong because I've seen a lot of people praise gpt-oss.
Completely agree. I was working on something with TensorRT LLM and threw Nemotron in there more on a whim. It completely mopped the floor with other models for my task (text style transfer), following joint moderation with another LLM & humans. Really impressed.
You may want to use the new "derestricted" variants of gpt-oss. While the ostensible goal of these variants is to de-censor them, it ends up removing the models' obsession with policy and wasting thinking tokens that could be used towards actually reasoning through a problem.
Great advice. Have you observed any other differences? I’ve been wondering if there are any specialized variants yet of GPT-OSS models yet that outperform on specific tasks (similar to the countless Llama 3 variants we’ve seen).
Im upvoting, im happy to finally see open source model with commercial use from Nvidia as most of the models ive been checking from you guys couldnt be used in commercial settings. Bravo Nvidia!
I've noticed that open models have made huge efficiency gains in the past several months. Some amount of that is explainable as architectural improvements but it seems quite obvious that a huge portion of the gains come from the heavy use of synthetic training data.
In this case roughly 33% of the training tokens are synthetically generated by a mix of other open weight models. I wonder if this trend is sustainable or if it might lead to model collapse as some have predicted. I suspect that the proliferation of synthetic data throughout open weight models has lead to a lot of the ChatGPT writing style replication (many bullet points, em dashes, it's not X but actually Y, etc).
The claim that a small, fast, and decently accurate model makes a good foundation for agentic workloads seems like a reasonable claim.
However, is cost the biggest limiting factor for agent adoption at this point? I would suspect that the much harder part is just creating an agent that yields meaningful results.
can it understand input in and generate output for different language tokens? does it know narrow IPA transcription of sentences in arbitrary languages?
I find it really interesting that it uses a Mamba hybrid with Transformers. Is it the only significant model right now using (at least partially) SSM layers? This must contribute to lower VRAM requirements right? Does it impact how KV caching works?
I would say it is weird, that NVidia competes with own customers but looking back at "Founders Edition" cards maybe it isn't that weird at all. The better question probably is - with every big corporation having its own LLM, what exactly is OpenAI moat that would explain their valuation?
after testing it for a little I am pretty disappointed. While I do get 90 token per second out of it from my M4 Pro which is more than enough for a real world use case, the quality is just not there. I gave it a codebase that it should analyze and answer me some questions and it started hallucinating right away. No replacement for a "real" coding agent - maybe for other agentic work like sorting emails though.
FWIW It runs on my 9060xt(AMD) 16gb, without any tweaks just fine. It's very useable.
I asked it to write a prime sieve in c#, started responding in .38 seconds, and wrote an implementation @ 20 tokens/sec
Is it fair to view this release as Nvidia strategically flexing that they can compete with their own customers in the model layer -- that they can be as vertically integrated as, say, GDM?
31 comments
[ 3.8 ms ] story [ 65.7 ms ] threadHowever, this looks like it has great potential for cost-effectiveness. As of today it's free to use over API on OpenRouter, so a bit unclear what it'll cost when it's not free, but free is free!
https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b:free
* Hybrid MoE: 2-3x faster than pure MoE transformers
* 1M context length
* Trained on NVFP4
* Open Source! Pretraining, mid-training, SFT and RL dataset released (SFT HF link is 404...)
* Open model training recipe (coming soon)
Really appreciate Nvidia being the most open lab but they really should make sure all the links/data are available on day 0.
Also interesting that the model is trained in NVFP4 but the inference weights are FP8.
As someone else mentioned, the GPT-OSS models are also quite good (though I haven’t found how to make them great yet, though I think they might age well like the Llama 3 models did and get better with time!).
But for a defined task, I’ve found task compliance, understanding, and tool call success rates to be some of the highest on these Nvidia models.
For example, I have a continuous job that evaluates if the data for a startup company on aVenture.vc could have overlapping/conflated two similar but unrelated companies for news articles, research details, investment rounds, etc… which is a token hungry ETL task! And I recently retested this workflow on the top 15 or so models today with <125b parameters, and the Nvidia models were among the best performing for this type of work, particularly around non-hallucination if given adequate grounding.
Also, re: cost - I run local inference on several machines that run continuously, in addition to routing through OpenRouter and the frontier providers, and was pleasantly surprised to find that if I’m a paying customer of OpenRouter otherwise, the free variant there from Nvidia is quite generous for limits, too.
I’ve used several runtimes, including vLLM. Works great! Speedy. Best results with Ubuntu after trying a few different distributions and Vulkan and ROCm drivers.
I recently pitted gpt-oss 120b against Qwen3-Next 80b on a lot of internal benchmarks (for production use), and for me, gpt-oss was slightly slower (vLLM, both fit in VRAM), much worse at multilingual tasks (33 languages evaluated), and had worse instruction following (e.g., Qwen3-Next was able to reuse the same prompts I used for Gemma3 perfectly, while gpt-oss struggled and RAG benchmarks suddenly went from 90% to 60% without additional prompt engineering).
And that's with Qwen3-Next being a random unofficial 4-bit quant (compared to gpt-oss having native support) + I had to disable multi-token prediction in Qwen3-Next because vLLM crashed with it.
Has someone here tried both gpt-oss 120b and Qwen3-Next 80b? Maybe I was doing something wrong because I've seen a lot of people praise gpt-oss.
But we are talking about LLM model here not software, but the same principle should applies.
[1] Open-source license:
https://en.wikipedia.org/wiki/Open-source_license
I've noticed that open models have made huge efficiency gains in the past several months. Some amount of that is explainable as architectural improvements but it seems quite obvious that a huge portion of the gains come from the heavy use of synthetic training data.
In this case roughly 33% of the training tokens are synthetically generated by a mix of other open weight models. I wonder if this trend is sustainable or if it might lead to model collapse as some have predicted. I suspect that the proliferation of synthetic data throughout open weight models has lead to a lot of the ChatGPT writing style replication (many bullet points, em dashes, it's not X but actually Y, etc).
I'm guessing there's some sophistication in the instrumentation I'm just not up to date with.
However, is cost the biggest limiting factor for agent adoption at this point? I would suspect that the much harder part is just creating an agent that yields meaningful results.
It scores at 9.6% hallucination rate, similar to qwen3-next-80b-a3b-thinking (9.3%) but of course it is much smaller.
https://github.com/vectara/hallucination-leaderboard
Other LLMs with the "nano" moniker are around 1b parameters or less.
https://github.com/jameschrisa/Ollama_Tuning_Guide/blob/main...
The default chat template is incorrect though and will fail but I published a corrected one you can replace it with: https://gist.github.com/omarkamali/a594b6cb07347f501babed489...