Hardware

GeForce RTX 2080 Super

GeForce RTX 2080 Super has 8 GB GDDR6 and 496 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (8 GB), 32 GB system RAM, and DDR5-5600 for anything that spills. Updated 2026-10-17.

Memory8 GB GDDR6

Bandwidth496 GB/s

Kindgpu

Year2019

256-bit GDDR6 at 15.5 Gbps = 496 GB/s. Source.

RSS for new models on this device

Models that fit

Model	Verdict	Quant	Context	tok/s
GLM 4.6V Flash 9.4B	Tight fit	Q5_K_S	8K	39–53
GLM Z1 9B 0414 9.4B	Tight fit	Q5_K_S	8K	39–53
GLM 4 9B 0414 9.4B	Tight fit	Q5_K_S	8K	39–53
GLM 4.1V 9B Thinking 9.4B	Tight fit	Q5_K_S	8K	39–53
Qwen3.5 9B 9.0B	Tight fit	UD-Q5_K_XL	8K	39–53
MiMo V2.6 Distill Qwen 9B 9.0B	Tight fit	Q5_K_M	4K	39–53
gemma 4 12b it 11.9B	Tight fit	IQ4_XS	4K	34–47
Ministral 3 8B Instruct 2512 8.5B	Tight fit	UD-Q5_K_XL	4K	41–56
Ministral 3 8B Reasoning 2512 8.5B	Tight fit	UD-Q5_K_XL	4K	41–56
Qwen3.8 27B 27.3B	Tight fit	UD-IQ1_M	4K	39–53
Qwen3 VL 8B Instruct 8.2B	Tight fit	UD-Q5_K_XL	8K	38–52
DeepSeek R1 0528 Qwen3 8B 8.2B	Tight fit	UD-Q5_K_XL	8K	38–52
Qwen3 8B 8.2B	Tight fit	UD-Q5_K_XL	8K	38–52
gemma 3 27b it 27.0B	Tight fit	UD-IQ1_S	1K	39–53
Qwen3 VL 8B Thinking 8.2B	Tight fit	UD-Q5_K_XL	8K	39–53
medgemma 27b text it 27.0B	Tight fit	UD-IQ1_S	2K	36–49
DeepSeek R1 Distill Llama 8B 8.0B	Tight fit	UD-Q5_K_XL	8K	40–55
Llama 3.1 8B Instruct 8.0B	Tight fit	UD-Q5_K_XL	8K	40–55
Apertus 8B Instruct 2509 8.1B	Tight fit	UD-Q5_K_XL	8K	40–54
Qwen2.5 7B Instruct 7.6B	Runs	Q5_K_M	8K	46–63
Qwen2.5 VL 7B Instruct 7.6B	Tight fit	Q6_K	8K	41–55
DeepSeek R1 Distill Qwen 7B 7.6B	Tight fit	Q6_K	8K	41–55
Qwen2.5 Coder 7B Instruct 128K 7.6B	Tight fit	Q6_K	8K	41–55
gemma 4 E4B it 7.5B	Tight fit	UD-Q5_K_XL	8K	37–51
Devstral Small 2 24B Instruct 2512 23.6B	Tight fit	UD-IQ1_M	4K	41–56
Mistral Small 3.2 24B Instruct 2506 23.6B	Tight fit	UD-IQ1_M	4K	41–56
Magistral Small 2509 23.6B	Tight fit	UD-IQ2_XXS	2K	38–52
Qwen2.5 14B Instruct 14.8B	Tight fit	Q3_K_S	2K	39–53
gemma 4 E4B it qat 7.5B	Runs	UD-Q4_K_XL	8K	55–76
Olmo 3 7B Instruct 7.3B	Tight fit	UD-Q4_K_XL	4K	41–55
Qwen3 14B 14.8B	Tight fit	UD-IQ3_XXS	4K	41–56
Ministral 3 14B Instruct 2512 13.5B	Tight fit	Q3_K_S	4K	40–55
Ministral 3 14B Reasoning 2512 13.5B	Tight fit	Q3_K_S	4K	40–55
LFM2.5 8B A1B 8.5B	Tight fit	UD-Q5_K_XL	8K	236–321
NousResearch Hermes 4 14B 14.8B	Tight fit	IQ3_XXS	4K	41–56
Qwen2.5 Coder 14B Instruct 128K 14.8B	Tight fit	Q2_K	4K	41–57
gemma 4 E2B it 4.6B	Runs	UD-Q8_K_XL	8K	49–67
Qwen3.5 4B 4.2B	Tight fit	UD-Q8_K_XL	8K	44–60
Qwen3 4B 4.0B	Tight fit	UD-Q8_K_XL	8K	44–59
Qwen3 VL 4B Instruct 4.0B	Tight fit	UD-Q8_K_XL	8K	44–59

90 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 Super at Q5_K_S, 8K context, about 39–53 tok/s. Weights 6.24 GB plus 0.31 GB of KV cache — 6.91 GB of 7.13 GB usable. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).