Hardware

GeForce RTX 4080

GeForce RTX 4080 has 16 GB GDDR6X and 716.8 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 GDDR6X

Bandwidth716.8 GB/s

Kindgpu

Year2022

256-bit GDDR6X at 22.4 Gbps = 716.8 GB/s. 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	27–36
Devstral Small 2 24B Instruct 2512 23.6B	Tight fit	Q4_K_M	4K	26–36
Mistral Small 3.2 24B Instruct 2506 23.6B	Tight fit	Q4_K_M	4K	26–36
Magistral Small 2509 23.6B	Tight fit	Q4_K_M	4K	26–36
Swift Qwen3.8 27B 27.3B	Tight fit	Q3_K_L	8K	27–36
gpt oss 20b 20.9B	Tight fit	UD-Q8_K_XL	8K	98–133
gemma 3 27b it 27.0B	Tight fit	UD-Q3_K_XL	8K	22–30
medgemma 27b text it 27.0B	Tight fit	UD-Q3_K_XL	8K	22–30
Qwen3.6 27B 26.9B	Tight fit	UD-Q3_K_XL	4K	27–36
Qwen3.5 27B 26.9B	Tight fit	UD-Q3_K_XL	4K	27–37
GLM 4.7 Flash REAP 23B A3B 23.0B	Tight fit	UD-Q4_K_XL	8K	171–234
GLM 4 32B 0414 32.6B	Tight fit	Q3_K_S	8K	26–36
NousResearch Hermes 4 14B 14.8B	Runs	Q5_K_M	8K	33–45
Qwen2.5 14B Instruct 14.8B	Runs	Q5_K_M	8K	33–44
DeepSeek R1 Distill Qwen 14B 14.8B	Tight fit	Q6_K	8K	29–39
Qwen2.5 Coder 14B Instruct 128K 14.8B	Tight fit	Q6_K	8K	29–39
Qwen3 14B 14.8B	Tight fit	UD-Q6_K_XL	8K	27–37
phi 4 14.7B	Tight fit	Q6_K	8K	29–39
gemma 4 26B A4B it 25.2B	Tight fit	UD-IQ4_XS	8K	95–129
gemma 4 31B it 30.7B	Tight fit	Q3_K_S	4K	23–31
Qwen3 32B 32.8B	Tight fit	UD-IQ3_XXS	4K	28–38
Qwen3 VL 32B Instruct 32.8B	Tight fit	UD-IQ3_XXS	4K	28–38
bottlecapai ThinkingCap gemma 4 26B A4B it 25.2B	Tight fit	IQ4_XS	8K	92–126
GLM 4.7 Flash 29.9B	Tight fit	UD-Q3_K_XL	8K	117–159
Qwen3.5 35B A3B 34.7B	Tight fit	UD-IQ3_S	8K	293–400
Qwen3.6 35B A3B 34.7B	Tight fit	UD-IQ3_S	8K	292–398
Ministral 3 14B Instruct 2512 13.5B	Tight fit	UD-Q6_K_XL	8K	29–40
Ministral 3 14B Reasoning 2512 13.5B	Tight fit	UD-Q6_K_XL	8K	29–40
Qwen3 Coder 30B A3B Instruct 30.5B	Tight fit	UD-Q3_K_XL	8K	182–249
Qwen3 30B A3B Instruct 2507 30.5B	Tight fit	UD-Q3_K_XL	8K	182–248
Qwen3 VL 30B A3B Instruct 30.5B	Tight fit	UD-Q3_K_XL	8K	182–248
Qwen3 30B A3B Thinking 2507 30.5B	Tight fit	UD-Q3_K_XL	8K	182–248
Qwen2.5 Coder 32B Instruct 32.8B	Tight fit	IQ3_XXS	8K	26–36
gemma 4 12b it 11.9B	Tight fit	UD-Q8_K_XL	8K	23–32
Tiel Coder 35B A3B 34.7B	Tight fit	UD-IQ3_XXS	8K	301–410
Qwen3.6 14B A3B FableVibes 13.8B	Tight fit	Q8_0	8K	117–160
LFM2.5 24B A2B 24.0B	Runs	UD-Q3_K_XL	8K	249–339
Kwaipilot KAT Coder V2.5 Dev 34.7B	Tight fit	IQ3_XXS	4K	142–193
Qwen2.5 32B Instruct 32.8B	Runs	IQ2_S	8K	31–43
GLM 4.6V Flash 9.4B	Runs	UD-Q8_K_XL	8K	32–43

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 4080 at UD-IQ4_XS, 8K context, about 27–36 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).