FitMyLLM
▸ NVIDIA· PASCAL

NVIDIA GeForce GTX 1080 Ti

VRAM
11 GB
ENTRY-LEVEL
BANDWIDTH
484
GB/S
MODELS Q4
189/331
57%
7B Q4 SPEED
~55
BLAZING
▸ MODEL COVERAGE @ Q457% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
~129
TOK/S
7B
~55
TOK/S
14B
~28
TOK/S
32B
—
18.0GB NEEDED
70B
—
39.4GB NEEDED
▸ SPECIFICATIONS
VRAM
11 GB
BANDWIDTH
484 GB/s
FP16 COMPUTE
0.2 TFLOPS
TDP
250W
MEMORY
GDDR5X
ARCHITECTURE
Pascal
CUDA CORES
3,584
PCIE
Gen 3 x16
177
FAST MODELS · >30 TOK/S
Real-time chat speed
189
USABLE · >10 TOK/S
Comfortable for all tasks
189
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test GeForce GTX 1080 Ti (or anything bigger) without committing. Pay by the second, cancel anytime.

Rent on RunPod →Or Vast.ai →

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 189
S
nomic-embed-text-v1.5 100M0.1B
EMBEDDING·8K CTX· CHAT
3872
TOK/S · 5% VRAM
›
S
GPT-2 124M0.124B
GPT2·1K CTX· CHAT
3123
TOK/S · 5% VRAM
›
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
2868
TOK/S · 5% VRAM
›
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
1156
TOK/S · 6% VRAM
›
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
1156
TOK/S · 6% VRAM
›
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
1156
TOK/S · 6% VRAM
›
S
GPT-2 Medium 345M0.345B
GPT2·1K CTX· CHAT
1122
TOK/S · 6% VRAM
›
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
1076
TOK/S · 6% VRAM
›
S
Falcon-H1 0.5B0.5B
FALCON·128K CTX· CHAT
774
TOK/S · 7% VRAM
›
S
Qwen 1.5 0.5B0.5B
QWEN·32K CTX· CHAT
774
TOK/S · 7% VRAM
›
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
774
TOK/S · 7% VRAM
›
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
682
TOK/S · 8% VRAM
›
S
Qwen3 0.6B0.6B
QWEN·32K CTX· CHAT· REASONING
645
TOK/S · 8% VRAM
›
S
GPT-2 Large 774M0.774B
GPT2·1K CTX· CHAT
500
TOK/S · 9% VRAM
›
S
Qwen 3.5 0.8B0.8B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
484
TOK/S · 9% VRAM
›
S
Qwen3.5-0.8B0.9B
QWEN·256K CTX· CHAT
430
TOK/S · 9% VRAM
›
S
Falcon3-1B1B
FALCON·32K CTX· CHAT
387
TOK/S · 10% VRAM
›
S
InternLM2 1B1B
INTERNLM·32K CTX· CHAT
387
TOK/S · 10% VRAM
›
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
352
TOK/S · 11% VRAM
›
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
323
TOK/S · 11% VRAM
›
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
323
TOK/S · 11% VRAM
›
S
DeepSeek Coder 1.3B1.3B
DEEPSEEK·16K CTX· CODING
298
TOK/S · 12% VRAM
›
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
298
TOK/S · 12% VRAM
›
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
298
TOK/S · 12% VRAM
›
S
Phi-1 1.3B1.3B
PHI·2K CTX· CODING
298
TOK/S · 12% VRAM
›
S
Phi-1.5 1.3B1.3B
PHI·2K CTX· CHAT· CODING
298
TOK/S · 12% VRAM
›
S
granite-4.0-h-tiny 6.9B6.9BMoE
GRANITE·128K CTX· CHAT
258
TOK/S · 43% VRAM
›
S
Falcon-H1 1.5B1.5B
FALCON·128K CTX· CHAT· CODING
258
TOK/S · 13% VRAM
›
S
GPT-2 XL 1.5B1.5B
GPT2·1K CTX· CHAT
258
TOK/S · 13% VRAM
›
S
Qwen2.5-Coder-1.5B1.5B
QWEN·32K CTX· CHAT· TOOL_USE· CODING
258
TOK/S · 13% VRAM
›
S
Qwen2 Math 1.5B1.5B
QWEN·4K CTX· REASONING
258
TOK/S · 13% VRAM
›
S
Qwen 2.5 1.5B1.5B
QWEN·32K CTX· CHAT· CODING
258
TOK/S · 13% VRAM
›
S
Yi Coder 1.5B1.5B
YI·125K CTX· CODING
258
TOK/S · 13% VRAM
›
S
stablelm-2-1_6b1.6B
STABLELM·4K CTX· CHAT
242
TOK/S · 13% VRAM
›
S
Qwen3 1.7B1.7B
QWEN·32K CTX· CHAT· REASONING
228
TOK/S · 14% VRAM
›
S
SmolLM2 1.7B1.71B
SMOLLM·8K CTX· CHAT
226
TOK/S · 14% VRAM
›
S
Qwen 1.5 1.8B1.8B
QWEN·32K CTX· CHAT
215
TOK/S · 14% VRAM
›
S
Moondream2 1.9B1.9B
OTHER·2K CTX· VISION· CHAT
204
TOK/S · 15% VRAM
›
S
Gemma 1 2B2B
GEMMA·8K CTX· CHAT
194
TOK/S · 16% VRAM
›
S
Granite 3.0 2B2B
GRANITE·128K CTX· CHAT· CODING
194
TOK/S · 16% VRAM
›
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce GTX 1080 Ti.

▸Find models for GeForce GTX 1080 TiCompare with other GPUs
▸ DEVICE UNDER TEST

NVIDIA GeForce GTX 1080 Ti — 11 GB VRAM.

▸ GEFORCE GTX 1080 TI SPEC
BRAND
NVIDIA
VRAM
11 GB GDDR5X
BANDWIDTH
484 GB/s
FP16 COMPUTE
0.2 TFLOPS
FP32 COMPUTE
11.3 TFLOPS
CUDA CORES
3,584
TDP
250 W
ARCHITECTURE
Pascal
▸ AI CAPABILITY
189/ 331 models @ Q4

With 11 GB VRAM and 484 GB/s bandwidth, this GPU handles models up to 15B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~55 tok/s.

§ 01TOP MODELS FOR GEFORCE GTX 1080 TI
189 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
StarCoder2 15B15B9.7 GB2626.5
DeepSeek R1 Distill Qwen 14B14.8B9.5 GB2643.9
DeepCoder 14B14.8B9.5 GB2638.7
Qwen2.5-Coder-14B14.8B9.5 GB2641.3
Qwen2.5-14B14.8B9.5 GB2641.3
Qwen3 14B14.8B9.5 GB2645.7
Ministral 3 14B14B9.0 GB2825.9
Phi-3-medium-14b14B9.0 GB2833.7
phi-4 14B14B9.0 GB2833.7
Phi-4-reasoning 14B14B9.0 GB2833.7
Phi-4-multimodal 14B14B9.0 GB2842.0
Qwen 1.5 14B14B9.0 GB2841.3
LLaVA-1.5 13B13.1B8.5 GB3052.1
Baichuan2 13B13B8.4 GB3023.6
Llama 2 13B13B8.4 GB3019.7
CodeLlama 13B13B8.4 GB3019.7
Vicuna 13B13B8.4 GB3011.8
LLaMA 1 13B13B8.4 GB3032.9
OPT 13B13B8.4 GB3035.8
Orca 2 13B13B8.4 GB3025.4