Which local LLMs can the GeForce RTX 5070 Ti run?

Assumes 32 GB of DDR5-5600 system RAM, Windows with this GPU driving the display, 8k context and an f16 KV cache.

Specs

VRAM: 16 GB
Memory bandwidth: 896.0 GB/s
FP16 compute: 44.1 TFLOPS
Launch year: 2025
Price: $949 street (as of 2026-08-09)

Verdicts at a glance

At Q4_K_M (or the closest available quant) with 8k context.

Runs great14 modelsRuns well2 modelsRuns slowly8 modelsWon't run5 models1 more model runs at a lower quant.

How to read the verdicts

Runs great: Fully on the GPU at 20 tok/s or more
Runs well: Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
Runs slowly: 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
Won't run: Does not fit, or under 2 tok/s

Every model on the GeForce RTX 5070 Ti

Dense models split between GPU and CPU slow down sharply — the CPU side sets the pace. MoE models that keep only their experts in system RAM degrade far more gently.

Scroll sideways to see every column.

29 models sorted by verdict and speed
Model	Verdict	Speed	Quant	Memory	Runs as	Context	Notes
EXAONE 4.0 1.2B	Runs great	est. 477.6 tok/s420.3–534.9calibrated estimate ±12%	Q4_K_M	2.5 / 16.0 GB	Full GPU	up to 64k	—
HyperCLOVA X SEED 1.5B	Runs great	est. 345.5 tok/s304.0–387.0calibrated estimate ±12%	Q4_K_M	3.0 / 16.0 GB	Full GPU	up to 16k	—
gpt-oss-20b	Runs great	189.5 tok/s8k estimate 176.3 tok/s (141.0–211.5, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	reasoning model
Kanana 1.5 15.7B-A3B	Runs great	est. 131.4 tok/s105.1–157.7calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—
DeepSeek R1 Distill Llama 8B	Runs great	est. 104.6 tok/s92.1–117.2calibrated estimate ±12%	Q4_K_M	7.2 / 16.0 GB	Full GPU	up to 64k	reasoning model
Kanana 1.5 8B	Runs great	est. 104.6 tok/s92.1–117.2calibrated estimate ±12%	Q4_K_M	7.2 / 16.0 GB	Full GPU	up to 32k	—
Llama 3.1 8B	Runs great	est. 104.6 tok/s92.1–117.2calibrated estimate ±12%	Q4_K_M	7.2 / 16.0 GB	Full GPU	up to 64k	—
Qwen3.5 9B	Runs great	est. 102.2 tok/s89.9–114.4calibrated estimate ±12%	Q4_K_M	7.3 / 16.0 GB	Full GPU	up to 128k	—
Qwen3 8B	Runs great	est. 100.5 tok/s88.5–112.6calibrated estimate ±12%	Q4_K_M	7.4 / 16.0 GB	Full GPU	up to 32k	—
Gemma 4 12B	Runs great	est. 81.9 tok/s72.1–91.7calibrated estimate ±12%	Q4_K_M	8.8 / 16.0 GB	Full GPU	up to 64k	—
Gemma 3 12B	Runs great	est. 80.0 tok/s70.4–89.6calibrated estimate ±12%	Q4_K_M	9.0 / 16.0 GB	Full GPU	up to 64k	—
HyperCLOVA X SEED Think 14B	Runs great	est. 61.5 tok/s43.1–80.0theoretical estimate ±30%	Q4_K_M	11.4 / 16.0 GB	Full GPU	up to 32k	reasoning model
Qwen3 14B	Runs great	est. 60.6 tok/s53.4–67.9calibrated estimate ±12%	Q4_K_M	11.5 / 16.0 GB	Full GPU	up to 32k	—
Phi-4	Runs great	est. 58.5 tok/s51.4–65.5calibrated estimate ±12%	Q4_K_M	11.9 / 16.0 GB	Full GPU	up to 16k	reasoning model
Mistral Small 3.2 24B	Runs well	est. 22.6 tok/s18.1–27.2calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 0.8 GB RAM	Partial offload	up to 8k	Not fully on the GPU — Runs great needs the whole model in GPU memory Try IQ4_XS: Runs great
Qwen3.5 35B-A3B	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great
Gemma 4 26B-A4B	Runs slowly	est. 58.8 tok/s41.1–76.4theoretical estimate ±30%	Q4_K_M	16.0 / 16.0 GB + 2.5 GB RAM	Partial offload	up to 256k	Less than 90% on the GPU — a GPU/CPU split is capped at Runs slowly UD-Q2_K_XL (heavy quality loss): Runs great
Qwen3 30B-A3B (2507)	Runs slowly	est. 19.2 tok/s13.4–24.9theoretical estimate ±30%	Q4_K_M	2.9 / 16.0 GB + 17.7 GB RAM	MoE experts in RAM	up to 64k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs well Q2_K (heavy quality loss): Runs great
Gemma 3 27B	Runs slowly	est. 12.6 tok/s10.1–15.2calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.4 GB RAM	Partial offload	up to 64k	Less than 90% on the GPU — a GPU/CPU split is capped at Runs slowly Try IQ4_XS: Runs well Q2_K (heavy quality loss): Runs great
Qwen3.5 27B	Runs slowly	est. 11.3 tok/s9.0–13.6calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.8 GB RAM	Partial offload	up to 128k	Less than 90% on the GPU — a GPU/CPU split is capped at Runs slowly Try IQ4_XS: Runs well UD-Q2_K_XL (heavy quality loss): Runs great
EXAONE 4.0 32B	Runs slowly	est. 7.2 tok/s5.7–8.6calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.1 GB RAM	Partial offload	up to 64k	reasoning model
EXAONE 4.5 33B	Runs slowly	est. 6.4 tok/s5.1–7.7calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	reasoning model
Qwen3 32B	Runs slowly	est. 5.1 tok/s4.0–6.1calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 7.1 GB RAM	Partial offload	up to 32k	Q2_K (heavy quality loss): Runs great
DeepSeek R1 Distill Qwen 32B	Runs slowly	est. 5.0 tok/s4.0–6.0calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 7.2 GB RAM	Partial offload	up to 16k	Q2_K (heavy quality loss): Runs great reasoning model
Llama 3.3 70B	Won't runTry Q2_K (heavy quality loss): Runs slowly	est. 2.7 tok/s2.2–3.2calibrated estimate ±20%	Q2_K	16.0 / 16.0 GB + 14.2 GB RAM	Partial offload	up to 16k	—
gpt-oss-120b	Won't run	—	MXFP4	needs 64.3 GB	—	—	Needs about 64.3 GB; 15.4 GB of VRAM and 28.0 GB of RAM are free With 96 GB RAM: Runs slowly reasoning model
Qwen3.5 122B-A10B	Won't run	—	Q4_K_M	needs 79.0 GB	—	—	Needs about 79.0 GB; 15.4 GB of VRAM and 28.0 GB of RAM are free With 96 GB RAM: Runs slowly
Solar Open 100B	Won't run	—	Q4_K_M	needs 64.4 GB	—	—	Needs about 64.4 GB; 15.4 GB of VRAM and 28.0 GB of RAM are free With 64 GB RAM: Runs slowly
Solar Open 2 250B	Won't run	—	IQ4_XS	needs 137.2 GB	—	—	Needs about 137.2 GB; 15.4 GB of VRAM and 28.0 GB of RAM are free With 128 GB RAM: Runs slowly

Reasoning models spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s).

Measured results on the GeForce RTX 5070 Ti

Public benchmarks we calibrate against. Their conditions (context, backend, flags) can differ from the estimates above.

Measured results on the GeForce RTX 5070 Ti
Model	Quant	Backend	Context	Prompt (tok/s)	Generation (tok/s)	Flags	Source	Measured
llama-2-7b	Q4_0	llama.cpp	512	6,952.0	176.9	—	github.com	2025-08-01
gpt-oss-20b	MXFP4	llama.cpp	2k	6,326.0	189.5	—	github.com	2025-08-15

Frequently asked questions

What is the largest model that runs entirely on the GeForce RTX 5070 Ti?

Mistral Small 3.2 24B at IQ4_XS (a 12.76 GB file) fits entirely in 16 GB with 8k context, at est. 44.5 tok/s (39.1–49.8, calibrated estimate ±12%).

How many local LLMs run well on the GeForce RTX 5070 Ti?

At Q4_K_M with 8k context, out of 29 tracked models: 14 run great, 2 run well, 8 run slowly and 5 won't run.

Can the GeForce RTX 5070 Ti run a 70B model like Llama 3.3 70B?

Runs slowly — Partial offload, Q2_K (heavy quality loss): est. 2.7 tok/s (2.2–3.2, calibrated estimate ±20%).

Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.