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.
A Mac counts when its report names the product, or when only that product was sold with its chip and memory.
Apple Silicon 48-96 GB· Mac Studio only
70B-class models fit at 4 bits. Memory speed 410 to 1,229 GB/s across the 8 devices with reports, so a typical figure here spans all of them. 79 single-device reports.
| # | Model | Reports | Gen t/s | PP t/s | With speculation |
|---|---|---|---|---|---|
| 1 | Qwen3.8 Flash-Next125B · 6B active Alibaba · mostly UD-IQ4_XS Gen 42 t/s (1 run) · PP 621 t/s (1 run) · with speculation 118 t/s (2) | 10 | 42 1 run | 621 1 run | 118 2 runs |
| 2 | Qwen3.827B Alibaba · mostly Q4_K_M Gen 19 t/s (2 runs) · PP 120 t/s (1 run) | 6 | 19 2 runs, 2 devices | 120 1 run | none |
| 3 | Qwen3.635B · 3B active Alibaba · mostly UD-Q4_K_XL Gen 100 t/s (4 runs) · PP 3333 t/s (3 runs) | 5 | 100 4 runs, 3 devices | 3333 3 runs | none |
| 4 | Qwen3.59B Alibaba · mostly Q4_K_M Gen 76 t/s (2 runs) · PP 1338 t/s (2 runs) | 4 | 76 2 runs, 2 devices | 1338 2 runs | none |
| 5 | Gemma 431B Google DeepMind · mostly Q4_K_M Gen 24 t/s (2 runs) · PP 345 t/s (2 runs) | 4 | 24 2 runs, 2 devices | 345 2 runs | none |
| 6 | Qwen3.535B · 3B active Alibaba · mostly 4-bit Gen 110 t/s (3 runs) · PP 1808 t/s (3 runs) | 3 | 110 3 runs, 2 devices | 1808 3 runs | none |
| 7 | Gemma 426B · 4B active Google DeepMind · mostly UD-Q4_K_M Gen 99 t/s (2 runs) · PP 1901 t/s (2 runs) | 3 | 99 2 runs, 2 devices | 1901 2 runs | none |
| 8 | Gemma 312B Google · mostly 4-bit Gen 64 t/s (2 runs) · PP 1778 t/s (2 runs) | 3 | 64 2 runs | 1778 2 runs | none |
| 9 | Qwen30.6B Alibaba · mostly 4-bit Gen 514 t/s (2 runs) · PP 22991 t/s (2 runs) | 2 | 514 2 runs | 22991 2 runs | none |
| 10 | Llama 3.21B Meta · mostly 4-bit Gen 440 t/s (1 run) · PP 16968 t/s (1 run) | 2 | 440 1 run | 16968 1 run | none |
| 11 | Qwen31.7B Alibaba · mostly 4-bit Gen 327 t/s (2 runs) · PP 11928 t/s (2 runs) | 2 | 327 2 runs | 11928 2 runs | none |
| 12 | Gemma 31B Google · mostly 4-bit Gen 295 t/s (1 run) · PP 16750 t/s (1 run) | 2 | 295 1 run | 16750 1 run | none |
| 13 | Llama 3.23B Meta · mostly 4-bit Gen 200 t/s (1 run) · PP 6123 t/s (1 run) | 2 | 200 1 run | 6123 1 run | none |
| 14 | Qwen34B Alibaba · mostly 4-bit Gen 173 t/s (2 runs) · PP 5239 t/s (2 runs) | 2 | 173 2 runs | 5239 2 runs | none |
| 15 | Gemma 34B Google · mostly 4-bit Gen 163 t/s (2 runs) · PP 5656 t/s (2 runs) | 2 | 163 2 runs | 5656 2 runs | none |
| 16 | Qwen330B · 3B active Alibaba · mostly 4-bit Gen 149 t/s (1 run) · PP 3497 t/s (1 run) | 2 | 149 1 run | 3497 1 run | none |
| 17 | Qwen 2.5 Coder7B mostly 4-bit Gen 114 t/s (2 runs) · PP 3132 t/s (2 runs) | 2 | 114 2 runs | 3132 2 runs | none |
| 18 | Qwen38B Alibaba · mostly 4-bit Gen 104 t/s (2 runs) · PP 2948 t/s (2 runs) | 2 | 104 2 runs | 2948 2 runs | none |
| 19 | Qwen314B Alibaba · mostly 4-bit Gen 60 t/s (2 runs) · PP 1661 t/s (2 runs) | 2 | 60 2 runs | 1661 2 runs | none |
| 20 | Qwen 2.5 Coder14B mostly 4-bit Gen 58 t/s (2 runs) · PP 1633 t/s (2 runs) | 2 | 58 2 runs | 1633 2 runs | none |
| 21 | Gemma 327B Google · mostly 4-bit Gen 30 t/s (1 run) · PP 751 t/s (1 run) | 2 | 30 1 run | 751 1 run | none |
| 22 | Qwen332B Alibaba · mostly 4-bit Gen 27 t/s (2 runs) · PP 699 t/s (2 runs) | 2 | 27 2 runs | 699 2 runs | none |
| 23 | Qwen 2.5 Coder32B mostly 4-bit Gen 27 t/s (2 runs) · PP 710 t/s (2 runs) | 2 | 27 2 runs | 710 2 runs | none |
| 24 | Gemma 4 E2B5.1B Google DeepMind · mostly Q4_K_M Gen 174 t/s (1 run) · PP 7021 t/s (1 run) | 1 | 174 1 run | 7021 1 run | none |
| 25 | Qwen3.54B Alibaba · mostly Q4_K_M Gen 136 t/s (1 run) · PP 4100 t/s (1 run) | 1 | 136 1 run | 4100 1 run | none |
| 26 | Gemma 4 E4B8B Google DeepMind · mostly Q4_K_M Gen 111 t/s (1 run) · PP 4217 t/s (1 run) | 1 | 111 1 run | 4217 1 run | none |
| 27 | gpt-oss117B · 5.1B active OpenAI · mostly MXFP4 Gen 73 t/s (1 run) · PP 347 t/s (1 run) | 1 | 73 1 run | 347 1 run | none |
| 28 | Qwen3.527B Alibaba · mostly Q4_K_M Gen 29 t/s (1 run) · PP 731 t/s (1 run) | 1 | 29 1 run | 731 1 run | none |
| 29 | Qwen3.8 27B dense27B Alibaba · mostly Q4_K_M Gen 21 t/s (1 run) · PP 144 t/s (1 run) | 1 | 21 1 run | 144 1 run | none |
| 30 | Qwen3-Coder30B · 3B active mostly Q4_K_M No generation data | 1 | no generation data | no PP data | none |
| 31 | Qwen3-Next80B · 3B active Alibaba · mostly 4-bit No generation data | 1 | no generation data | no PP data | none |
| 32 | Qwen3.8 Qwen3.8-27B27B Alibaba · mostly Q4_K_M No generation data | 1 | no generation data | no PP data | none |
| 33 | Qwen3.8 Swift-1.527B Alibaba · mostly 4.7bpw No generation data | 1 | no generation data | no PP data | none |
| 34 | Qwen3.8 Swift-1.5 Flash-Next125B · 6B active Alibaba · mostly IQ3_S No generation data · with speculation 145 t/s (1) | 1 | no generation data | no PP data | 145 1 run |
Not in the table: 56 reports don't say which model size ran.
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.