Hardware

GeForce RTX 5080

GeForce RTX 5080 has 16 GB GDDR7 and 960 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (16 GB), 32 GB system RAM, and DDR5-5600 for anything that spills. Updated 2026-10-24.

Memory16 GB GDDR7

Bandwidth960 GB/s

Kindgpu

Year2025

NVIDIA official compare table: memory config and bandwidth. Source.

RSS for new models on this device

Models that fit

Model	Verdict	Quant	Context	tok/s
Qwen3.8 27B 27.3B	Tight fit	UD-IQ4_XS	8K	36–49
Devstral Small 2 24B Instruct 2512 23.6B	Tight fit	Q4_K_M	4K	35–48
Mistral Small 3.2 24B Instruct 2506 23.6B	Tight fit	Q4_K_M	4K	35–48
Magistral Small 2509 23.6B	Tight fit	Q4_K_M	4K	35–48
Swift Qwen3.8 27B 27.3B	Tight fit	Q3_K_L	8K	36–48
gpt oss 20b 20.9B	Tight fit	UD-Q8_K_XL	8K	131–179
gemma 3 27b it 27.0B	Tight fit	UD-Q3_K_XL	8K	30–40
medgemma 27b text it 27.0B	Tight fit	UD-Q3_K_XL	8K	30–40
Qwen3.6 27B 26.9B	Tight fit	UD-Q3_K_XL	4K	36–49
Qwen3.5 27B 26.9B	Tight fit	UD-Q3_K_XL	4K	36–49
GLM 4.7 Flash REAP 23B A3B 23.0B	Tight fit	UD-Q4_K_XL	8K	229–313
GLM 4 32B 0414 32.6B	Tight fit	Q3_K_S	8K	35–48
NousResearch Hermes 4 14B 14.8B	Runs	Q5_K_M	8K	45–61
Qwen2.5 14B Instruct 14.8B	Runs	Q5_K_M	8K	44–59
DeepSeek R1 Distill Qwen 14B 14.8B	Tight fit	Q6_K	8K	38–52
Qwen2.5 Coder 14B Instruct 128K 14.8B	Tight fit	Q6_K	8K	38–52
Qwen3 14B 14.8B	Tight fit	UD-Q6_K_XL	8K	36–49
phi 4 14.7B	Tight fit	Q6_K	8K	39–53
gemma 4 26B A4B it 25.2B	Tight fit	UD-IQ4_XS	8K	127–173
gemma 4 31B it 30.7B	Tight fit	Q3_K_S	4K	31–42
Qwen3 32B 32.8B	Tight fit	UD-IQ3_XXS	4K	38–51
Qwen3 VL 32B Instruct 32.8B	Tight fit	UD-IQ3_XXS	4K	38–51
bottlecapai ThinkingCap gemma 4 26B A4B it 25.2B	Tight fit	IQ4_XS	8K	123–168
GLM 4.7 Flash 29.9B	Tight fit	UD-Q3_K_XL	8K	157–214
Qwen3.5 35B A3B 34.7B	Tight fit	UD-IQ3_S	8K	393–536
Qwen3.6 35B A3B 34.7B	Tight fit	UD-IQ3_S	8K	391–533
Ministral 3 14B Instruct 2512 13.5B	Tight fit	UD-Q6_K_XL	8K	39–53
Ministral 3 14B Reasoning 2512 13.5B	Tight fit	UD-Q6_K_XL	8K	39–53
Qwen3 Coder 30B A3B Instruct 30.5B	Tight fit	UD-Q3_K_XL	8K	244–333
Qwen3 30B A3B Instruct 2507 30.5B	Tight fit	UD-Q3_K_XL	8K	244–333
Qwen3 VL 30B A3B Instruct 30.5B	Tight fit	UD-Q3_K_XL	8K	244–333
Qwen3 30B A3B Thinking 2507 30.5B	Tight fit	UD-Q3_K_XL	8K	244–333
Qwen2.5 Coder 32B Instruct 32.8B	Tight fit	IQ3_XXS	8K	35–48
gemma 4 12b it 11.9B	Tight fit	UD-Q8_K_XL	8K	31–43
Tiel Coder 35B A3B 34.7B	Tight fit	UD-IQ3_XXS	8K	403–549
Qwen3.6 14B A3B FableVibes 13.8B	Tight fit	Q8_0	8K	157–214
LFM2.5 24B A2B 24.0B	Runs	UD-Q3_K_XL	8K	333–454
Kwaipilot KAT Coder V2.5 Dev 34.7B	Tight fit	IQ3_XXS	4K	190–259
Qwen2.5 32B Instruct 32.8B	Runs	IQ2_S	8K	42–57
GLM 4.6V Flash 9.4B	Runs	UD-Q8_K_XL	8K	43–58

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 5080 at UD-IQ4_XS, 8K context, about 36–49 tok/s. Weights 13.3 GB plus 0.57 GB of KV cache — 14.3 GB of 14.7 GB usable. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).