Hardware

GeForce GTX 1080 Ti

GeForce GTX 1080 Ti has 11 GB GDDR5X and 484 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (11 GB), 32 GB system RAM, and DDR5-5600 for anything that spills. Updated 2026-10-24.

Memory11 GB GDDR5X
Bandwidth484 GB/s
Kindgpu
Year2017

352-bit GDDR5X at 11 Gbps = 484 GB/s. Source.

RSS for new models on this device

Models that fit

ModelVerdictQuantContexttok/s
Qwen3 14B
14.8B
Tight fitUD-Q4_K_XL4K27–37
Ministral 3 14B Instruct 2512
13.5B
Tight fitQ5_K_S4K26–36
Ministral 3 14B Reasoning 2512
13.5B
Tight fitQ5_K_S4K26–36
Qwen2.5 14B Instruct
14.8B
Tight fitQ4_K_M4K27–37
NousResearch Hermes 4 14B
14.8B
Tight fitQ4_K_M4K28–38
DeepSeek R1 Distill Qwen 14B
14.8B
Tight fitQ4_K_M4K27–37
Qwen2.5 Coder 14B Instruct 128K
14.8B
Tight fitQ4_K_M4K27–37
phi 4
14.7B
Tight fitQ4_K_M4K27–37
gemma 4 12b it
11.9B
Tight fitUD-Q5_K_XL8K23–31
Qwen3.6 14B A3B FableVibes
13.8B
Tight fitQ5_K_M8K115–157
Qwen3 32B
32.8B
Tight fitUD-IQ1_M4K28–39
Qwen3 VL 32B Instruct
32.8B
Tight fitUD-IQ1_M4K28–39
Qwen2.5 32B Instruct
32.8B
Tight fitIQ2_XXS2K28–38
Qwen2.5 Coder 32B Instruct
32.8B
Tight fitIQ2_XXS2K28–38
GLM 4 32B 0414
32.6B
Tight fitUD-IQ2_XXS8K27–37
GLM 4.6V Flash
9.4B
Tight fitUD-Q6_K_XL8K29–39
GLM Z1 9B 0414
9.4B
Tight fitUD-Q6_K_XL8K29–39
GLM 4 9B 0414
9.4B
Tight fitUD-Q6_K_XL8K29–39
gemma 4 31B it
30.7B
Tight fitUD-IQ2_XXS4K21–29
Qwen3.8 9B Distill
9.2B
Tight fitQ8_04K27–37
Qwen3.5 9B
9.0B
Tight fitQ8_08K27–37
MiMo V2.6 Distill Qwen 9B
9.0B
Tight fitQ8_08K27–37
Qwythos 9B Claude Mythos 5 1M
9.0B
Tight fitQ8_08K27–37
Qwythos 9B v2
9.0B
Tight fitQ8_08K27–37
granite 4.2 8b
8.8B
Tight fitQ8_04K27–36
Devstral Small 2 24B Instruct 2512
23.6B
Tight fitUD-Q2_K_XL4K27–36
Mistral Small 3.2 24B Instruct 2506
23.6B
Tight fitUD-Q2_K_XL4K27–36
Magistral Small 2509
23.6B
Tight fitUD-Q2_K_XL4K27–36
Ministral 3 8B Instruct 2512
8.5B
Tight fitQ8_04K28–38
Ministral 3 8B Reasoning 2512
8.5B
Tight fitQ8_04K28–38
Qwen3.8 27B
27.3B
Tight fitUD-IQ2_S8K30–41
Swift Qwen3.8 27B
27.3B
Tight fitIQ2_XXS8K28–38
Qwen3.5 27B
26.9B
Tight fitUD-IQ2_XXS8K29–40
Qwen3.6 27B
26.9B
Tight fitUD-IQ2_XXS8K27–37
Qwen3 VL 8B Instruct
8.2B
Tight fitQ8_08K27–37
DeepSeek R1 0528 Qwen3 8B
8.2B
Tight fitQ8_08K27–37
Qwen3 8B
8.2B
Tight fitQ8_08K27–37
Qwen3 VL 8B Thinking
8.2B
Tight fitQ8_08K27–37
gemma 3 27b it
27.0B
Tight fitUD-IQ2_XXS8K22–30
medgemma 27b text it
27.0B
Tight fitUD-IQ2_XXS8K22–30

105 more models in the catalog do not fit this default profile, or ranked below the first 40 that do.

Example: Tight fit fully on your GeForce GTX 1080 Ti at UD-Q4_K_XL, 4K context, about 27–37 tok/s. Weights 8.53 GB plus 0.63 GB of KV cache — 9.54 GB of 9.97 GB usable. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).