What people run, by hardware
Pick the kind of machine you have. You'll see the model sizes people report running on it, most reported first, with the speed they typically get. It tells you what works on hardware like yours. It doesn't tell you which model gives the best answers.
To check a specific model on your exact card, use the calculator. For coding, see the coding models by VRAM.
AMD and Intel 48 GB+· AMD only
Datacenter AMD and Intel accelerators. Memory speed 864 to 5,300 GB/s across the 3 devices with reports, so a typical figure here spans all of them. 8 single-device reports.
| # | Model | Reports | Gen t/s | PP t/s | With speculation |
|---|---|---|---|---|---|
| 1 | Qwen3-Coder30B · 3B active mostly BF16 Gen 185 t/s (2 runs) | 2 | 185 2 runs | no PP data | none |
| 2 | Qwen3.8 Flash-Next125B · 6B active Alibaba · mostly IQ3_XXS Gen 90 t/s (1 run) | 2 | 90 1 run | no PP data | none |
| 3 | Qwen3.827B Alibaba · mostly Q8_0 No generation data | 2 | no generation data | no PP data | none |
| 4 | LFM2.524B · 2.5B active Liquid AI · mostly Q8 Gen 95 t/s (1 run) | 1 | 95 1 run | no PP data | none |
| 5 | RWKV72.9B mostly F16 Gen 49 t/s (1 run) · PP 4316 t/s (1 run) | 1 | 49 1 run | 4316 1 run | none |
Not in the table: 1 ran on more than one device, which says nothing about what one of them does.
How this list works
Each row is one model size, because a 27B and a 397B from the same family are different choices. Rows are ordered by how many people report running that size on this hardware.
Generation speed is the median of runs on one device, serving one request, without speculative decoding. PP is the median prompt-processing speed from plain runs that reported it, so its run count can be smaller. Speculative decoding (MTP, a draft model, DFlash, n-gram lookup) can make the same model several times faster, so those runs get their own column. A report that doesn't make clear which kind of run it was counts in neither.
Hardware is grouped by how much it holds and how fast its memory is, since memory speed sets how fast a model writes. Click a model for every report behind its row.