Hardware

GeForce RTX 4090

GeForce RTX 4090 has 24 GB GDDR6X and 1008 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (24 GB), 32 GB system RAM, and DDR5-5600 for anything that spills. Updated 2026-10-24.

Memory24 GB GDDR6X

Bandwidth1008 GB/s

Kindgpu

Year2022

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
GLM 4 32B 0414 32.6B	Tight fit	Q5_K_S	4K	24–33
gemma 4 31B it 30.7B	Tight fit	Q5_K_S	4K	22–30
Qwen3 32B 32.8B	Tight fit	UD-Q4_K_XL	8K	25–34
Qwen3 VL 32B Instruct 32.8B	Tight fit	UD-Q4_K_XL	8K	25–34
Qwen2.5 32B Instruct 32.8B	Tight fit	Q4_K_M	8K	25–34
Qwen2.5 Coder 32B Instruct 32.8B	Tight fit	Q4_K_M	8K	25–34
DeepSeek R1 Distill Qwen 32B 32.8B	Tight fit	Q4_K_M	8K	25–34
Swift Qwen3.8 27B 27.3B	Tight fit	Q5_K_M	8K	27–36
Qwen3.8 27B 27.3B	Tight fit	UD-Q6_K	8K	25–34
gemma 3 27b it 27.0B	Tight fit	Q6_K	4K	23–31
medgemma 27b text it 27.0B	Tight fit	Q6_K	4K	23–31
Qwen3.6 27B 26.9B	Tight fit	Q6_K	4K	24–33
Qwen3.5 27B 26.9B	Tight fit	Q6_K	4K	24–33
Devstral Small 2 24B Instruct 2512 23.6B	Tight fit	UD-Q6_K_XL	8K	25–34
Mistral Small 3.2 24B Instruct 2506 23.6B	Tight fit	UD-Q6_K_XL	8K	25–34
Magistral Small 2509 23.6B	Tight fit	UD-Q6_K_XL	8K	25–34
Qwen3.5 35B A3B 34.7B	Tight fit	UD-Q4_K_XL	8K	265–361
Qwen3.6 35B A3B 34.7B	Tight fit	UD-Q4_K_XL	8K	264–359
Tiel Coder 35B A3B 34.7B	Tight fit	UD-Q4_K_XL	8K	264–359
GLM 4.7 Flash 29.9B	Tight fit	UD-Q5_K_XL	8K	110–150
Kwaipilot KAT Coder V2.5 Dev 34.7B	Tight fit	Q4_K_M	8K	137–187
Cyber Tiel Coder 35B A3B GGUF MTP 35.5B	Tight fit	Q4_K_M (est.)	8K	279–381
Qwen3.8 35B A3B Distill 35.5B	Tight fit	Q4_K_M	8K	277–378
Qwen3 Coder 30B A3B Instruct 30.5B	Tight fit	UD-Q5_K_XL	8K	188–257
Qwen3 30B A3B Instruct 2507 30.5B	Tight fit	UD-Q5_K_XL	8K	188–257
Qwen3 VL 30B A3B Instruct 30.5B	Tight fit	UD-Q5_K_XL	8K	188–257
Qwen3 30B A3B Thinking 2507 30.5B	Tight fit	UD-Q5_K_XL	8K	188–257
DeepSeek R1 Distill Llama 70B 70.6B	Tight fit	UD-IQ2_XXS	8K	25–34
Llama 3.3 70B Instruct 70.6B	Tight fit	UD-IQ2_XXS	8K	25–34
Hermes 4 70B 70.6B	Tight fit	UD-IQ2_XXS	8K	25–34
bottlecapai ThinkingCap gemma 4 26B A4B it 25.2B	Tight fit	Q5_K_M	8K	107–146
gemma 4 26B A4B it 25.2B	Tight fit	UD-Q5_K_XL	8K	103–141
NVIDIA Nemotron 3.5 Lightning 30B A3B 32.9B	Tight fit	IQ4_NL	8K	234–319
Qwen3 Coder Next 79.7B	Tight fit	UD-IQ1_M	8K	124–169
Nemotron 3 Nano 30B A3B 31.6B	Tight fit	Q4_K_S	8K	219–299
NVIDIA Nemotron 3 Nano Omni 30B A3B Reasoning 31.6B	Tight fit	UD-IQ4_XS	8K	242–330
LFM2.5 24B A2B 24.0B	Tight fit	UD-Q6_K_XL	8K	222–303
Qwen3 Next 80B A3B Thinking 79.7B	Tight fit	UD-IQ1_S	2K	524–715
GLM 4.7 Flash REAP 23B A3B 23.0B	Tight fit	UD-Q6_K_XL	8K	180–245
gpt oss 20b 20.9B	Runs great	UD-Q8_K_XL	8K	138–188

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 4090 at Q5_K_S, 4K context, about 24–33 tok/s. Weights 21.0 GB plus 0.24 GB of KV cache — 21.7 GB of 22.3 GB usable. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).