https://www.datasculpting.ai/inference/ Mon, 26 Oct 2026 11:30:27 +0000 MyBB https://www.datasculpting.ai/inference/showthread.php?tid=1484 Sun, 18 Oct 2026 17:12:00 +0000 mangowire]]> https://www.datasculpting.ai/inference/showthread.php?tid=1484 https://www.datasculpting.ai/inference/showthread.php?tid=1217 Thu, 15 Oct 2026 02:53:19 +0000 batchscope72]]> https://www.datasculpting.ai/inference/showthread.php?tid=1217
This isn't revolutionary, but the combination of TensorRT-LLM and A6000 felt surprisingly usable once I tuned around speculative decoding.

If someone wants the exact settings I can clean them up and post them.]]>
This isn't revolutionary, but the combination of TensorRT-LLM and A6000 felt surprisingly usable once I tuned around speculative decoding.

If someone wants the exact settings I can clean them up and post them.]]> https://www.datasculpting.ai/inference/showthread.php?tid=1144 Tue, 13 Oct 2026 23:29:11 +0000 thetaplane]]> https://www.datasculpting.ai/inference/showthread.php?tid=1144
This isn't revolutionary, but the combination of LM Studio and M3 Max felt surprisingly usable once I tuned around small local stacks.

If someone wants the exact settings I can clean them up and post them.]]>
This isn't revolutionary, but the combination of LM Studio and M3 Max felt surprisingly usable once I tuned around small local stacks.

If someone wants the exact settings I can clean them up and post them.]]> https://www.datasculpting.ai/inference/showthread.php?tid=995 Sat, 10 Oct 2026 06:53:58 +0000 quiettoken]]> https://www.datasculpting.ai/inference/showthread.php?tid=995
I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling tokens/sec.

Would appreciate practical advice rather than theory.

This is mostly for local work rather than public serving.]]>
I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling tokens/sec.

Would appreciate practical advice rather than theory.

This is mostly for local work rather than public serving.]]> https://www.datasculpting.ai/inference/showthread.php?tid=915 Fri, 09 Oct 2026 04:49:59 +0000 quiettoken]]> https://www.datasculpting.ai/inference/showthread.php?tid=915
This isn't revolutionary, but the combination of Ollama and GB200 felt surprisingly usable once I tuned around tool calling.

Feel free to tear it apart if you see something dumb.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.]]>
This isn't revolutionary, but the combination of Ollama and GB200 felt surprisingly usable once I tuned around tool calling.

Feel free to tear it apart if you see something dumb.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.]]> https://www.datasculpting.ai/inference/showthread.php?tid=922 Thu, 08 Oct 2026 22:27:40 +0000 plainworks]]> https://www.datasculpting.ai/inference/showthread.php?tid=922
It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with small local stacks.

Maybe obvious to some of you, but it clicked for me this week.]]>
It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with small local stacks.

Maybe obvious to some of you, but it clicked for me this week.]]> https://www.datasculpting.ai/inference/showthread.php?tid=859 Thu, 08 Oct 2026 02:23:37 +0000 thetaplane]]> https://www.datasculpting.ai/inference/showthread.php?tid=859
Maybe useful as a starting point: vLLM on mini PC, keeping HBM constraints in mind from the start.

Feel free to tear it apart if you see something dumb.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.]]>
Maybe useful as a starting point: vLLM on mini PC, keeping HBM constraints in mind from the start.

Feel free to tear it apart if you see something dumb.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.]]> https://www.datasculpting.ai/inference/showthread.php?tid=788 Tue, 06 Oct 2026 00:11:01 +0000 emberpeak]]> https://www.datasculpting.ai/inference/showthread.php?tid=788
I'm comparing two approaches here: keep it simple on B200, or squeeze more out of the stack and deal with the complexity.

Interested in tradeoffs more than fan loyalty.]]>
I'm comparing two approaches here: keep it simple on B200, or squeeze more out of the stack and deal with the complexity.

Interested in tradeoffs more than fan loyalty.]]> https://www.datasculpting.ai/inference/showthread.php?tid=648 Fri, 02 Oct 2026 00:56:32 +0000 plainworks]]> https://www.datasculpting.ai/inference/showthread.php?tid=648
Two paths both seem viable, but they break down differently once structured output becomes important.

What would you pick if you had to live with it for a few months? Turns out 'just one more test' was a lie.]]>
Two paths both seem viable, but they break down differently once structured output becomes important.

What would you pick if you had to live with it for a few months? Turns out 'just one more test' was a lie.]]> https://www.datasculpting.ai/inference/showthread.php?tid=646 Thu, 01 Oct 2026 21:19:14 +0000 quiettoken]]> https://www.datasculpting.ai/inference/showthread.php?tid=646
I'm mostly working with Phi in Ollama on A6000. The part I'm trying to understand is continuous batching.

Not looking for the perfect answer, mostly what worked in real use.]]>
I'm mostly working with Phi in Ollama on A6000. The part I'm trying to understand is continuous batching.

Not looking for the perfect answer, mostly what worked in real use.]]> https://www.datasculpting.ai/inference/showthread.php?tid=605 Thu, 01 Oct 2026 04:50:30 +0000 northquill]]> https://www.datasculpting.ai/inference/showthread.php?tid=605
It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with token cost.

Wondering if this is just where the whole space is heading now.]]>
It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with token cost.

Wondering if this is just where the whole space is heading now.]]> https://www.datasculpting.ai/inference/showthread.php?tid=554 Mon, 28 Sep 2026 23:50:52 +0000 quiettoken]]> https://www.datasculpting.ai/inference/showthread.php?tid=554
Just sharing a setup that ended up working reasonably well: Mistral, LM Studio, 7900 XTX, with a lot of attention on VRAM headroom.

If someone wants the exact settings I can clean them up and post them.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.]]>
Just sharing a setup that ended up working reasonably well: Mistral, LM Studio, 7900 XTX, with a lot of attention on VRAM headroom.

If someone wants the exact settings I can clean them up and post them.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.]]> https://www.datasculpting.ai/inference/showthread.php?tid=510 Sun, 27 Sep 2026 03:23:26 +0000 emberpeak]]> https://www.datasculpting.ai/inference/showthread.php?tid=510
I tried this with Mixtral using Ollama on M3 Max. The headline result was better than I expected, but MoE serving still ended up being the limiting factor.

Nothing scientific here, just practical notes from a real setup.]]>
I tried this with Mixtral using Ollama on M3 Max. The headline result was better than I expected, but MoE serving still ended up being the limiting factor.

Nothing scientific here, just practical notes from a real setup.]]> https://www.datasculpting.ai/inference/showthread.php?tid=421 Tue, 22 Sep 2026 17:03:45 +0000 sanevault]]> https://www.datasculpting.ai/inference/showthread.php?tid=421
After a few runs on mini PC, I ended up with decent performance, but the setup only really made sense once I adjusted around router policy.

Happy to post more details if anyone wants them.

I care more about stability than squeezing the last possible tokens/sec out of it.]]>
After a few runs on mini PC, I ended up with decent performance, but the setup only really made sense once I adjusted around router policy.

Happy to post more details if anyone wants them.

I care more about stability than squeezing the last possible tokens/sec out of it.]]> https://www.datasculpting.ai/inference/showthread.php?tid=350 Sat, 19 Sep 2026 02:27:00 +0000 cobaltlab]]> https://www.datasculpting.ai/inference/showthread.php?tid=350
One thing I keep noticing is that people underestimate INT4 until they actually try to run this stuff for more than one afternoon.

Maybe obvious to some of you, but it clicked for me this week.]]>
One thing I keep noticing is that people underestimate INT4 until they actually try to run this stuff for more than one afternoon.

Maybe obvious to some of you, but it clicked for me this week.]]>