+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: Routers (https://www.datasculpting.ai/inference/forumdisplay.php?fid=45)
+--- Thread: dataset format recommendations: early impressions (/showthread.php?tid=1141)
Pages:
1
2
dataset format recommendations: early impressions - batchember - 10-13-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: FLUX, vLLM, M3 Max, with a lot of attention on quant drift.
Maybe useful as a starting point for newer folks.
Re: dataset format recommendations: early impressions - phasenode - 10-14-2026
Quote:Thought I'd post a small recipe because a lot of threads ask similar things.
A couple things I'd check first. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: dataset format recommendations: early impressions - emberquill - 10-14-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at HBM constraints.
Re: dataset format recommendations: early impressions - promptpoint - 10-14-2026
I tested this tonight. On M3 Max with Ollama, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
Re: dataset format recommendations: early impressions - plainworks - 10-14-2026
Quote:I tested this tonight. On M3 Max with Ollama, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput col
subscribed, curious where this lands.
Re: dataset format recommendations: early impressions - audioforge - 10-17-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4. Not glamorous advice, but repeatable baselines save a lot of time.
Re: dataset format recommendations: early impressions - phaseport36 - 10-17-2026
Ran a quick check on my box. On Threadripper box with Ollama, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
Re: dataset format recommendations: early impressions - audioforge - 10-17-2026
Quote:Ran a quick check on my box. On Threadripper box with Ollama, I saw basically the same behavior. The surprise was that memory pressure showed up befor
A couple things I'd check first. On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
Re: dataset format recommendations: early impressions - forgemixer - 10-18-2026
Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Worth testing the simpler explanation before adopting the more interesting one. Turns out 'just one more test' was a lie.
Re: dataset format recommendations: early impressions - routeline23 - 10-18-2026
Quote:Good point. I don't think your conclusion is far off.
Appreciate the detail. That matches what I saw on 7900 XTX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.