Hardware

GeForce GTX 1080

GeForce GTX 1080 has 8 GB GDDR5X and 320 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (8 GB), 32 GB system RAM, and DDR5-5600 for anything that spills. Updated 2026-10-24.

Memory8 GB GDDR5X
Bandwidth320 GB/s
Kindgpu
Year2016

256-bit GDDR5X at 10 Gbps = 320 GB/s. Source.

RSS for new models on this device

Models that fit

ModelVerdictQuantContexttok/s
GLM 4.6V Flash
9.4B
Tight fitQ5_K_S8K25–34
GLM Z1 9B 0414
9.4B
Tight fitQ5_K_S8K25–34
GLM 4 9B 0414
9.4B
Tight fitQ5_K_S8K25–34
Qwen3.8 9B Distill
9.2B
Tight fitQ5_K_M8K25–35
Qwythos 9B Claude Mythos 5 1M
9.0B
Tight fitQ5_K_M8K26–36
Qwythos 9B v2
9.0B
Tight fitQ5_K_M8K26–35
Qwen3.5 9B
9.0B
Tight fitUD-Q5_K_XL8K25–34
MiMo V2.6 Distill Qwen 9B
9.0B
Tight fitQ5_K_M4K25–34
granite 4.2 8b
8.8B
Tight fitQ5_K_M4K25–35
gemma 4 12b it
11.9B
Tight fitIQ4_XS4K22–30
Ministral 3 8B Instruct 2512
8.5B
Tight fitUD-Q5_K_XL4K26–36
Ministral 3 8B Reasoning 2512
8.5B
Tight fitUD-Q5_K_XL4K26–36
Qwen3.8 27B
27.3B
Tight fitUD-IQ1_M4K25–34
Qwen3 VL 8B Instruct
8.2B
Tight fitUD-Q5_K_XL8K25–34
DeepSeek R1 0528 Qwen3 8B
8.2B
Tight fitUD-Q5_K_XL8K25–34
Qwen3 8B
8.2B
Tight fitUD-Q5_K_XL8K25–34
gemma 3 27b it
27.0B
Tight fitUD-IQ1_S1K25–34
Qwen3 VL 8B Thinking
8.2B
Tight fitUD-Q5_K_XL8K25–34
medgemma 27b text it
27.0B
Tight fitUD-IQ1_S2K23–32
DeepSeek R1 Distill Llama 8B
8.0B
Tight fitUD-Q5_K_XL8K26–35
Llama 3.1 8B Instruct
8.0B
Tight fitUD-Q5_K_XL8K26–35
Apertus 8B Instruct 2509
8.1B
Tight fitUD-Q5_K_XL8K26–35
Qwen2.5 7B Instruct
7.6B
RunsQ5_K_M8K30–41
Qwen2.5 VL 7B Instruct
7.6B
Tight fitQ6_K8K26–36
DeepSeek R1 Distill Qwen 7B
7.6B
Tight fitQ6_K8K26–36
Qwen2.5 Coder 7B Instruct 128K
7.6B
Tight fitQ6_K8K26–36
NVIDIA Nemotron 3.5 Bolt E4B
7.5B
RunsUD-Q5_K_XL8K27–37
gemma 4 E4B it
7.5B
Tight fitUD-Q5_K_XL8K24–33
Devstral Small 2 24B Instruct 2512
23.6B
Tight fitUD-IQ1_M4K26–36
Mistral Small 3.2 24B Instruct 2506
23.6B
Tight fitUD-IQ1_M4K26–36
Magistral Small 2509
23.6B
Tight fitUD-IQ2_XXS2K25–34
Qwen2.5 14B Instruct
14.8B
Tight fitQ3_K_S2K25–34
gemma 4 E4B it qat
7.5B
RunsUD-Q4_K_XL8K36–49
Olmo 3 7B Instruct
7.3B
Tight fitUD-Q4_K_XL4K26–36
Qwen3 14B
14.8B
Tight fitUD-IQ3_XXS4K26–36
Ministral 3 14B Instruct 2512
13.5B
Tight fitQ3_K_S4K26–36
Ministral 3 14B Reasoning 2512
13.5B
Tight fitQ3_K_S4K26–36
LFM2.5 8B A1B
8.5B
Tight fitUD-Q5_K_XL8K152–207
Qwen3.6 14B A3B FableVibes
13.8B
Tight fitQ3_K_M8K107–146
NousResearch Hermes 4 14B
14.8B
Tight fitIQ3_XXS4K27–36

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 GTX 1080 at Q5_K_S, 8K context, about 25–34 tok/s. Weights 6.24 GB plus 0.31 GB of KV cache — 6.91 GB of 7.13 GB usable. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).