NVIDIA GeForce RTX 4070 Ti

Ada's fastest 12 GB card: 672 GB/s with a 12 GB lid. The Super refresh later matched its speed with 16 GB — this one kept the lid.

12 GB GDDR6X 672 GB/s 192-bit bus 285 W TDP

Technical specifications

GPU die
AD103
CUDA cores
7680
Boost clock
~2.61 GHz
VRAM
12 GB GDDR6X
Memory bus
192-bit
Memory bandwidth
672 GB/s
PCIe
4.0 x16
NVLink
none
TDP
285 W
Release
Jan 2023

What these specs mean for llama.cpp

Speed without the room

672 GB/s is 33% ahead of the plain 4070's bus — token generation lands at ~75–100 t/s on 8B and ~45–58 t/s on 13B Q4, the best 12 GB numbers Ada produces, with prompt processing at ~850–1150 t/s. Then the 12 GB lid: 13B Q5 loads at 8K; 27B Q4 is 7 GB over; MoE 30B at full quant is out. The fastest 12 GB card in the series, and 12 GB is still a 13B tier.

The refresh that overshadowed it

Eight months later the 4070 Ti Super shipped: same 672 GB/s, 16 GB. Every LLM argument the 4070 Ti made — speed at mid price — the Super made with 4 more GB. If the two are close in price locally, the Super is the buy; the original Ti survives on discount.

Power

285 W (NVIDIA's revised TGP; early launch materials said 260) puts it a step above the Super's envelope. A 700 W PSU requirement, 3-slot-class cooling — this is the 4070 tier's power-hungry member.

The short form 13B at Q5, fast 8B at Q8, best 12 GB token speed Ada has — until the Super took the speed and added VRAM. Buy it discounted; otherwise, the 4070 Ti Super.

The MTP question: if your model ships a built-in multi-token-prediction head (Qwen 3.5/3.6/3.8, Gemma 4), the one-flag speculative pass (--spec-type draft-mtp --spec-draft-n-max 2 --parallel 1) is worth +45–65% (estimated) on token generation here; no 4070 Ti A/B in the record; the estimate sits at the 672 GB/s class, between the measured 3070-class and 3090-class results. The price is ~0.6–2 GB of VRAM, the output is bit-identical to the unaccelerated run, and models without MTP heads (Llama class) see nothing. Full tuning rules in the MTP guide.

Expected performance (Q4_K_M, single GPU)

ModelSize on GPUToken genToken gen (MTP est.)Prompt proc.Fits?
8B Q8_0~9.7 GB~75–100 t/s~109–165 t/s~800–1100 t/s✅ 32K+ ctx
13B Q4_K_M~8.5 GB~45–58 t/s~65–95 t/s~850–1150 t/s✅ 32K+ ctx
13B Q5_K_M~11.9 GB~32–42 t/s~46–69 t/s~700–900 t/s⚠️ 8K ctx
27B Q4_K_M~19 GB———❌ ~7 GB over

MTP est. = rough prior with --spec-type draft-mtp for models that ship MTP heads (Qwen 3.5/3.6/3.8, Gemma 4); Llama-class models get no MTP speedup. Actual gains depend on model, quant, context length, llama.cpp build and your card — sweep --spec-draft-n-max, don't trust the column blindly. MTP guide →

Figures assume full offload (-ngl 99), ~8K context and batch 2048. Token speed tracks the memory bus almost linearly, so treat ranges as class estimates — your llama.cpp build and the model's attention layout shift them.

27B models (Qwen class) — Q4 / Q5 / Q6 / Q8

QuantGGUF size1× 4070 Ti (12 GB)2× 4070 Ti (24 GB)
Q4_K_M~19 GB❌ ~7 GB over⚠️ ~20–26 t/s, 8K ctx
Q5_K_M~22 GB❌❌ ~2 GB over
Q6_K~25 GB❌❌
Q8_0~33 GB❌❌

27B is a hard no single-card. A pair (24 GB) runs Q4_K_M at 8K — a clear margin over 2× 4070; 3× (36 GB) reaches Q5 at 8–16K around ~18–23 t/s. The speed story is good; the VRAM story is the 4070's, two sizes down.

Practical tips

Multi-card: 2×, 3×, 4×

PCIe 4.0, ~25–35% tax, 12 GB tiles: 2× hits the 27B Q4 line, 3× hits Q5.

BuildGPU powerVRAM13B Q827B Q4_K_M27B Q5_K_M
2× 4070 Ti570 W24 GB~52–68 t/s⚠️ ~20–26 t/s, 8K ctx❌ ~2 GB over
3× 4070 Ti855 W36 GB(overkill)~24–30 t/s, 16K+ ctx~18–23 t/s, 8–16K ctx

The 3-way build (855 W, 36 GB) is a serious 27B Q5 box — and a serious power draw. It needs three working x8/x16 lanes, which is where consumer boards stop.

The Super shadow 2× 4070 Ti Super (570 W, 32 GB) does the same 27B Q4/Q5 work with 8 more GB at the same total power. The original Ti's multi-card case only stands on discount pricing.

Offloading (CPU RAM)

When a model won't fit, -ngl N parks the tail layers on the CPU. The mental model that saves pain: offloaded layers don't run at a fraction of GPU speed — they run at CPU speed. Handy moves: peel the last 2–4 layers off to reclaim ~0.5–1 GB of VRAM for almost nothing; keep MoE experts on CPU with --n-cpu-moe; park the output embedding with -ot output=CPU on big models. Budget 32 GB system RAM for 27B-class offload, 64 GB for 70B. And never offload the KV cache — the session becomes unusable.

3-card example llama-server -m 27b-q5_k_m.gguf -ngl 99 -sm layer -c 16384 --tensor-split 1,1,1

Recommended llama.cpp command

llama-server -m llama-3.1-13b-q5_k_m.gguf -ngl 99 -c 8192 -b 2048 -ub 2048 --host 127.0.0.1 --port 8080

Verdict

The fastest 12 GB Ada, and a footnote to its own refresh: the 4070 Ti Super matches its speed with 4 GB more VRAM. At a real discount the Ti is a fine 13B-Q5 card and a fast 27B half-rig; at close prices, the Super wins by default.

← RTX 4070 Super next: RTX 4070 Ti Super →