RTX 4080 SUPER
44 records across 9 models (quants: 13.21 GB, 5.95 GB, IQ1_S, IQ2_M, IQ2_XXS, IQ3_XXS, IQ4_XS, MXFP4, Q4_0, Q4_K, Q4_K_M, UD-IQ3_XXS, UD-Q3_K_XL, unspecified).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 4080 SUPER | Bonsai 2 27B | 5.95 GB | llama.cpp (CUDA) | 85 | – | – | – | 262144 | 2026-10-08 | community | – | source |
| RTX 4080 SUPER | Bonsai 2 27B | 5.95 GB | llama.cpp (CUDA) | – | 2278 | – | – | 262144 | 2026-10-08 | community | – | source |
| RTX 4080 SUPER | gpt-oss 20B 20B | MXFP4 | llama.cpp | 139.1 | 6364.0 | – | – | 4096 | – | sourced | – | source |
| RTX 4080 SUPER | gpt-oss 20B 20B | MXFP4 | llama.cpp | 123.0 | 4708.7 | – | – | 16384 | – | sourced | – | source |
| RTX 4080 SUPER | gpt-oss 20B 20B | MXFP4 | llama.cpp | 107.2 | 3328.1 | – | – | 32768 | – | sourced | – | source |
| RTX 4080 SUPER | gpt-oss 20B 20B | MXFP4 | llama.cpp | 81.5 | 1961.5 | – | – | 65536 | – | sourced | – | source |
| RTX 4080 SUPER | gpt-oss 20B 20B | MXFP4 | llama.cpp | 60.0 | 1145.0 | – | – | 131072 | – | sourced | – | source |
| RTX 4080 SUPER | LFM2.5-8B-A1B | IQ1_S | llama.cpp (CUDA) | 241.8 | – | – | – | 8192 | 2026-10-04 | community | – | source |
| RTX 4080 SUPER | LFM2.5-8B-A1B | IQ2_XXS | llama.cpp (CUDA) | 224.1 | – | – | – | 8192 | 2026-10-04 | community | – | source |
| RTX 4080 SUPER | LFM2.5-8B-A1B | IQ2_M | llama.cpp (CUDA) | 208.5 | – | – | – | 8192 | 2026-10-04 | community | – | source |
| RTX 4080 SUPER | LFM2.5-8B-A1B | IQ3_XXS | llama.cpp (CUDA) | 196.2 | – | – | – | 8192 | 2026-10-04 | community | – | source |
| RTX 4080 SUPER | LFM2.5-8B-A1B | Q4_K_M | llama.cpp (CUDA) | 172.4 | – | – | – | 8192 | 2026-10-04 | community | – | source |
| RTX 4080 SUPER | LFM2.5-8B-A1B | unspecified | llama.cpp (CUDA) | 118.5 | – | – | – | 8192 | 2026-10-04 | community | – | source |
| RTX 4080 SUPER | llama 7B | Q4_0 | llama.cpp (Vulkan) | 150.2 | 8007.37 | – | – | tg128 | 2025-10-18 | community | – | source |
| RTX 4080 SUPER | llama 7B | Q4_0 | llama.cpp (Vulkan) | 147.13 | 7101.18 | – | – | tg128 | 2025-10-18 | community | – | source |
| RTX 4080 SUPER | Qwen3 14B 14B | Q4_K | llama.cpp | 64.2 | 3745.0 | – | – | 4096 | – | sourced | – | source |
| RTX 4080 SUPER | Qwen3 14B 14B | Q4_K | llama.cpp | 52.8 | 2526.7 | – | – | 16384 | – | sourced | – | source |
| RTX 4080 SUPER | Qwen3 14B 14B | Q4_K | llama.cpp | 42.6 | 1769.3 | – | – | 32768 | – | sourced | – | source |
| RTX 4080 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 104.2 | 6137.0 | – | – | 4096 | – | sourced | – | source |
| RTX 4080 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 79.4 | 3858.1 | – | – | 16384 | – | sourced | – | source |
| RTX 4080 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 59.5 | 2537.1 | – | – | 32768 | – | sourced | – | source |
| RTX 4080 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 39.1 | 1501.5 | – | – | 65536 | – | sourced | – | source |
| RTX 4080 SUPER | Qwen3.8-27B | UD-Q3_K_XL | llama.cpp (CUDA) | 47 | – | – | – | 131072 | 2026-10-08 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-27B 27B | UD-Q3_K_XL | llama.cpp (CUDA) | 35.6 | – | – | – | – | 2026-08 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-27B 27B | UD-Q3_K_XL | llama.cpp (CUDA) | 33.9 | – | – | – | – | 2026-08 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-27B 27B | UD-Q3_K_XL | llama.cpp (CUDA) | 33.1 | – | – | – | – | 2026-08 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-27B 27B | UD-Q3_K_XL | llama.cpp (CUDA) | 1.4 | – | – | – | – | 2026-08 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-27B | UD-Q3_K_XL | llama.cpp (CUDA) | – | 2155 | – | – | 131072 | 2026-10-08 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp (CUDA) | 19.531 | – | – | – | 2048 | 2026-09 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp (CUDA) | 18.753 | – | – | – | 16384 | 2026-09 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp (CUDA) | 18.321 | – | – | – | 8192 | 2026-09 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp (CUDA) | 17.275 | – | – | – | 16384 | 2026-09 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp (CUDA) | 16.096 | – | – | – | 16384 | 2026-09 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp (CUDA) | 15.135 | – | – | – | 16384 | 2026-09 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp (CUDA) | 13.567 | – | – | – | 16384 | 2026-09 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp (CUDA) | 5.776 | – | – | – | 262144 | 2026-09 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp (CUDA) | 5.649 | – | – | – | 262144 | 2026-09 | community | – | source |
| RTX 4080 SUPER | Qwen3.8-Flash-Next | IQ4_XS | llama.cpp (CUDA) | 0.71 | – | – | – | 262144 | 2026-09 | community | – | source |
| RTX 4080 SUPER | Welp-35B-A3B | UD-IQ3_XXS | llama.cpp (CUDA) | 165 | – | – | – | 262144 | 2026-10-08 | community | – | source |
| RTX 4080 SUPER | Welp-35B-A3B | 13.21 GB | llama.cpp (CUDA) | 164 | – | – | – | 262144 | 2026-10-08 | community | – | source |
| RTX 4080 SUPER | Welp-35B-A3B | 13.21 GB | llama.cpp (CUDA) | 107 | – | – | – | 262144 | 2026-10-08 | community | – | source |
| RTX 4080 SUPER | Welp-35B-A3B | 13.21 GB | llama.cpp (CUDA) | – | 5111 | – | – | 262144 | 2026-10-08 | community | – | source |
| RTX 4080 SUPER | Welp-35B-A3B | UD-IQ3_XXS | llama.cpp (CUDA) | – | 5165 | – | – | 262144 | 2026-10-08 | community | – | source |
| RTX 4080 SUPER | Welp-35B-A3B | 13.21 GB | llama.cpp (CUDA) | – | 2043 | – | – | 262144 | 2026-10-08 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085