Hardware

GeForce RTX 2080 Ti

GeForce RTX 2080 Ti has 11 GB GDDR6 and 616 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 GDDR6

Bandwidth616 GB/s

Kindgpu

Year2018

352-bit GDDR6 at 14 Gbps = 616 GB/s. Source.

RSS for new models on this device

Models that fit

Model	Verdict	Quant	Context	tok/s
Qwen3 14B 14.8B	Tight fit	UD-Q4_K_XL	4K	34–47
Ministral 3 14B Instruct 2512 13.5B	Tight fit	Q5_K_S	4K	34–46
Ministral 3 14B Reasoning 2512 13.5B	Tight fit	Q5_K_S	4K	34–46
NousResearch Hermes 4 14B 14.8B	Tight fit	Q4_K_M	4K	35–48
Qwen2.5 14B Instruct 14.8B	Tight fit	Q4_K_M	4K	35–47
DeepSeek R1 Distill Qwen 14B 14.8B	Tight fit	Q4_K_M	4K	35–47
Qwen2.5 Coder 14B Instruct 128K 14.8B	Tight fit	Q4_K_M	4K	35–47
phi 4 14.7B	Tight fit	Q4_K_M	4K	35–47
gemma 4 12b it 11.9B	Tight fit	UD-Q5_K_XL	8K	29–39
Qwen3.6 14B A3B FableVibes 13.8B	Tight fit	Q5_K_M	8K	146–199
Qwen3 32B 32.8B	Tight fit	UD-IQ1_M	4K	36–49
Qwen3 VL 32B Instruct 32.8B	Tight fit	UD-IQ1_M	4K	36–49
Qwen2.5 32B Instruct 32.8B	Tight fit	IQ2_XXS	2K	35–48
Qwen2.5 Coder 32B Instruct 32.8B	Tight fit	IQ2_XXS	2K	35–48
GLM 4 32B 0414 32.6B	Tight fit	UD-IQ2_XXS	8K	35–47
GLM 4.6V Flash 9.4B	Tight fit	UD-Q6_K_XL	8K	37–50
GLM Z1 9B 0414 9.4B	Tight fit	UD-Q6_K_XL	8K	37–50
GLM 4 9B 0414 9.4B	Tight fit	UD-Q6_K_XL	8K	37–50
gemma 4 31B it 30.7B	Tight fit	UD-IQ2_XXS	4K	27–37
Qwen3.8 9B Distill 9.2B	Tight fit	Q8_0	4K	34–47
Qwen3.5 9B 9.0B	Tight fit	Q8_0	8K	35–47
MiMo V2.6 Distill Qwen 9B 9.0B	Tight fit	Q8_0	8K	35–47
Qwythos 9B Claude Mythos 5 1M 9.0B	Tight fit	Q8_0	8K	35–47
Qwythos 9B v2 9.0B	Tight fit	Q8_0	8K	35–47
granite 4.2 8b 8.8B	Tight fit	Q8_0	4K	34–46
Devstral Small 2 24B Instruct 2512 23.6B	Tight fit	UD-Q2_K_XL	4K	34–46
Mistral Small 3.2 24B Instruct 2506 23.6B	Tight fit	UD-Q2_K_XL	4K	34–46
Magistral Small 2509 23.6B	Tight fit	UD-Q2_K_XL	4K	34–46
Ministral 3 8B Instruct 2512 8.5B	Tight fit	Q8_0	4K	35–48
Ministral 3 8B Reasoning 2512 8.5B	Tight fit	Q8_0	4K	35–48
Qwen3.8 27B 27.3B	Tight fit	UD-IQ2_S	8K	38–52
Swift Qwen3.8 27B 27.3B	Tight fit	IQ2_XXS	8K	35–48
Qwen3.5 27B 26.9B	Tight fit	UD-IQ2_XXS	8K	37–51
Qwen3.6 27B 26.9B	Tight fit	UD-IQ2_XXS	8K	34–47
Qwen3 VL 8B Instruct 8.2B	Tight fit	Q8_0	8K	34–47
DeepSeek R1 0528 Qwen3 8B 8.2B	Tight fit	Q8_0	8K	34–47
Qwen3 8B 8.2B	Tight fit	Q8_0	8K	34–47
Qwen3 VL 8B Thinking 8.2B	Tight fit	Q8_0	8K	34–47
gemma 3 27b it 27.0B	Tight fit	UD-IQ2_XXS	8K	28–38
medgemma 27b text it 27.0B	Tight fit	UD-IQ2_XXS	8K	28–38

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 RTX 2080 Ti at UD-Q4_K_XL, 4K context, about 34–47 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).