GeForce RTX 5080

Name: GeForce RTX 5080
Brand: NVIDIA
Price: 53888 TWD

NVIDIA GeForce RTX 5080: 16 GB of memory at 960 GB/s. Below: the open models it can run, estimated at 16 GB with an 8K context. The highest-bandwidth 16 GB card here (960 GB/s): fast with models up to about 24B at 4-bit, but it holds no larger models than the $429 RTX 5060 Ti.

Last updated: 2026-10-14

Specifications

Memory	16 GB GDDR7[src]
Memory bandwidth	960 GB/s[src]
Power	360 W[src]
Launch	2025-01[src]
Launch price	US$999[src]
Architecture	Blackwell[src]
Software	CUDA

What it can run

Best-quality quantization that fits with a 8K context, and the estimated generation speed. Estimates, not benchmarks. See the methodology.

Model	Params	Best quant	Memory	tok/s (est.)
Gemma 4 26B A4B IT	25.2B (3.8B)	Q4_K_M	15.7 GiB	292
Mistral Small 3.2 24B Instruct (2506)	24B	Q4_K_M	16.0 GiB	46
Magistral Small 1.2 (2509)	24B	Q4_K_M	16.0 GiB	46
Devstral Small 2 24B Instruct (2512)	24B	Q4_K_M	16.0 GiB	46
gpt-oss-20b	21B (3.6B)	Q5_K_M	15.3 GiB	262
Phi-4 (14B)	14B	Q6_K	13.3 GiB	58
Gemma 3 12B IT	12B	Q8_0	13.8 GiB	53
Gemma 4 12B Unified IT	11.95B	Q8_0	13.3 GiB	53
Qwen3.5-9B	9B	Q8_0	10.1 GiB	70
Qwen3-8B	8.2B	Q8_0	10.1 GiB	77
DeepSeek-R1-0528-Qwen3-8B	8.19B	Q8_0	10.1 GiB	77
Llama 3.1 8B Instruct	8B	Q8_0	9.8 GiB	79
Gemma 4 E4B IT	8B	Q8_0	9.1 GiB	79
Llama 3.2 3B Instruct	3.21B	FP16	7.7 GiB	105
Kimi K2.6	1000B (32B)	Doesn't fit	–	–
DeepSeek-R1-0528 (671B)	671B (37B)	Doesn't fit	–	–
DeepSeek-V4-Flash	284B (13B)	Doesn't fit	–	–
Qwen3.8-Flash-Next	180B (6B)	Doesn't fit	–	–
Qwen3.5-122B-A10B	122B (10B)	Doesn't fit	–	–
Mistral Small 4 119B (2603)	119B (6.5B)	Doesn't fit	–	–
gpt-oss-120b	117B (5.1B)	Doesn't fit	–	–
Llama 4 Scout 17B-16E Instruct	109B (17B)	Doesn't fit	–	–
GLM-4.5-Air	106B (12B)	Doesn't fit	–	–
Qwen3-Coder-Next (80B-A3B)	80B (3B)	Doesn't fit	–	–
Llama 3.3 70B Instruct	70B	Doesn't fit	–	–
Qwen3.5-35B-A3B	35B (3B)	Doesn't fit	–	–
Qwen3.6-35B-A3B	35B (3B)	Doesn't fit	–	–
Qwen3-32B	32.8B	Doesn't fit	–	–
DeepSeek-R1-Distill-Qwen-32B	32.76B	Doesn't fit	–	–
Gemma 4 31B IT	30.7B	Doesn't fit	–	–
Qwen3-30B-A3B (2507)	30.5B (3.3B)	Doesn't fit	–	–
Qwen3-Coder-30B-A3B-Instruct	30.5B (3.3B)	Doesn't fit	–	–
GLM-4.7-Flash (30B-A3B)	30B (3B)	Doesn't fit	–	–
Qwen3.5-27B	27B	Doesn't fit	–	–
Qwen3.6-27B	27B	Doesn't fit	–	–
Qwen3.8-27B	27B	Doesn't fit	–	–
Gemma 3 27B IT	27B	Doesn't fit	–	–

Prices

Latest price at each shop, as listed on the day we checked.

Region	Shop	Listing	Price	Per GB	Checked
Taiwan	原價屋 CoolPC	｛INNO3D RTX5080 X3 OC｝2640MHz/30cm/註四年/超頻三風扇/註四年Line on the shop's public price list (no per-product page); list stamped 2026/10/14 15:47	NT$53,888	NT$3,368/GB	2026-10-14
US	NeweggGH ELECTRONICS	MSI SHADOW GeForce RTX 5080 16GB GDDR7 PCI Express 5.0 Graphics Card RTX 5080 16G SHADOW 3XNewegg marketplace seller	US$1,779	US$111/GB	2026-10-14

Taiwan value: about 138.6 tok/s on Llama 3.1 8B Instruct (Q4_K_M, 8K), or 2.6 tok/s per NT$1,000.
US value: about 138.6 tok/s on Llama 3.1 8B Instruct (Q4_K_M, 8K), or 7.8 tok/s per US$100.

A price history chart appears once we have checked this device on two or more days.

All prices →

Frequently asked questions

Which LLMs can the GeForce RTX 5080 run?

With 16 GB and an 8K context, the largest models that fit include: Gemma 4 26B A4B IT, Mistral Small 3.2 24B Instruct (2506), Magistral Small 1.2 (2509), Devstral Small 2 24B Instruct (2512), gpt-oss-20b. See the full table below.

How fast is the GeForce RTX 5080 for local LLMs?

Generation speed is mostly set by memory bandwidth (960 GB/s). For Llama 3.1 8B Instruct at Q8_0, expect roughly 79 tokens/s; bigger models are slower.

Can the GeForce RTX 5080 run 70B models?

Llama 3.3 70B Instruct does not fit on the GeForce RTX 5080 (16 GB), even at Q4_K_M with an 8K context.