Hardware

GeForce RTX 4080 Super

GeForce RTX 4080 Super has 16 GB GDDR6X and 736 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 2026-10-17.

Memory16 GB GDDR6X

Bandwidth736 GB/s

Kindgpu

Year2024

NVIDIA GeForce RTX 40-series specifications. Bandwidth is the published peak. 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	27–37
Devstral Small 2 24B Instruct 2512 23.6B	Tight fit	Q4_K_M	4K	27–37
Mistral Small 3.2 24B Instruct 2506 23.6B	Tight fit	Q4_K_M	4K	27–37
Magistral Small 2509 23.6B	Tight fit	Q4_K_M	4K	27–37
gpt oss 20b 20.9B	Tight fit	UD-Q8_K_XL	8K	100–137
gemma 3 27b it 27.0B	Tight fit	UD-Q3_K_XL	8K	23–31
medgemma 27b text it 27.0B	Tight fit	UD-Q3_K_XL	8K	23–31
Qwen3.6 27B 26.9B	Tight fit	UD-Q3_K_XL	4K	27–37
Qwen3.5 27B 26.9B	Tight fit	UD-Q3_K_XL	4K	28–38
GLM 4.7 Flash REAP 23B A3B 23.0B	Tight fit	UD-Q4_K_XL	8K	176–240
GLM 4 32B 0414 32.6B	Tight fit	Q3_K_S	8K	27–37
NousResearch Hermes 4 14B 14.8B	Runs	Q5_K_M	8K	34–47
Qwen2.5 14B Instruct 14.8B	Runs	Q5_K_M	8K	33–46
DeepSeek R1 Distill Qwen 14B 14.8B	Tight fit	Q6_K	8K	29–40
Qwen2.5 Coder 14B Instruct 128K 14.8B	Tight fit	Q6_K	8K	29–40
Qwen3 14B 14.8B	Tight fit	UD-Q6_K_XL	8K	28–38
phi 4 14.7B	Tight fit	Q6_K	8K	30–40
gemma 4 26B A4B it 25.2B	Tight fit	UD-IQ4_XS	8K	97–132
gemma 4 31B it 30.7B	Tight fit	Q3_K_S	4K	23–32
Qwen3 32B 32.8B	Tight fit	UD-IQ3_XXS	4K	29–39
Qwen3 VL 32B Instruct 32.8B	Tight fit	UD-IQ3_XXS	4K	29–39
GLM 4.7 Flash 29.9B	Tight fit	UD-Q3_K_XL	8K	120–164
Qwen3.5 35B A3B 34.7B	Tight fit	UD-IQ3_S	8K	301–411
Qwen3.6 35B A3B 34.7B	Tight fit	UD-IQ3_S	8K	300–408
Ministral 3 14B Instruct 2512 13.5B	Tight fit	UD-Q6_K_XL	8K	30–41
Ministral 3 14B Reasoning 2512 13.5B	Tight fit	UD-Q6_K_XL	8K	30–41
Qwen3 Coder 30B A3B Instruct 30.5B	Tight fit	UD-Q3_K_XL	8K	187–255
Qwen3 30B A3B Instruct 2507 30.5B	Tight fit	UD-Q3_K_XL	8K	187–255
Qwen3 VL 30B A3B Instruct 30.5B	Tight fit	UD-Q3_K_XL	8K	187–255
Qwen3 30B A3B Thinking 2507 30.5B	Tight fit	UD-Q3_K_XL	8K	187–255
Qwen2.5 Coder 32B Instruct 32.8B	Tight fit	IQ3_XXS	8K	27–37
gemma 4 12b it 11.9B	Tight fit	UD-Q8_K_XL	8K	24–33
LFM2.5 24B A2B 24.0B	Runs	UD-Q3_K_XL	8K	255–348
Kwaipilot KAT Coder V2.5 Dev 34.7B	Tight fit	IQ3_XXS	4K	146–199
Qwen2.5 32B Instruct 32.8B	Runs	IQ2_S	8K	32–44
GLM 4.6V Flash 9.4B	Runs	UD-Q8_K_XL	8K	33–44
GLM Z1 9B 0414 9.4B	Runs	UD-Q8_K_XL	8K	33–44
GLM 4 9B 0414 9.4B	Runs	UD-Q8_K_XL	8K	33–44
GLM 4.1V 9B Thinking 9.4B	Runs	UD-Q8_K_XL	8K	33–44
MiMo V2.6 Distill Qwen 9B 9.0B	Runs	Q8_0	8K	41–56

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 4080 Super at UD-IQ4_XS, 8K context, about 27–37 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).