NVIDIA GeForce RTX 3080 Ti

The most complete single card below 24 GB: 12 GB of GDDR6X at 960 GB/s. 13B models run fast and with real context headroom.

12 GB GDDR6X 960 GB/s 384-bit bus 350 W TDP

Technical specifications

GPU die
GA102
CUDA cores
10240
Boost clock
~1.67 GHz
VRAM
12 GB GDDR6X
Memory bus
384-bit
Memory bandwidth
960 GB/s
PCIe
4.0 x16
NVLink
none
TDP
350 W
Release
Jun 2021

What these specs mean for llama.cpp

960 GB/s — the fastest bandwidth under 24 GB

19 Gbps GDDR6X on the full 384-bit bus puts the 3080 Ti slightly ahead of the 3090's 936 GB/s for token generation. A 13B Q4_K_M streams at ~38–42 t/s — the single-card 13B experience in the lineup is as good as it gets below the 3090s. 8B models hit ~70 t/s: you'll be waiting for the model less often than for your own thoughts.

12 GB — fixes the 3080's one flaw

The 3080 10GB had to ration its KV cache; the Ti gives 13B Q4_K_M (~8.5 GB) a comfortable 3+ GB for context, meaning a real 8K–16K window, and 8B models can run at Q6/Q8 with room for 32K. It's the same "13B specialist" niche as the 3060 12GB — just at ~2× the speed and with faster prompt processing.

Compute — near-3090 class

10240 cores at ~1.67 GHz: ~1400–1600 t/s prompt processing on 13B. Long-context ingestion is quick, and this is also the strongest sub-3090 card for large batch sizes (e.g. generating many completions in parallel in llama-server).

Where it sits The 3080 Ti is the "fast 13B" card. The 3060 12GB is the "cheap 13B" card. The 3090 is the "anything up to ~24GB" card. If your budget is near the 3090's, the 3090's +12 GB usually outweighs the 3080 Ti's small speed edge — but as a second tile in a 3090 build, the 3080 Ti is a genuinely good fit (see below).

Before the numbers: if your model ships a built-in multi-token-prediction head (e.g. Qwen 3.5/3.6/3.8, Gemma 4), generation can be made faster with --spec-type draft-mtp --spec-draft-n-max 2 --parallel 1 — on this card that's worth +45–65% (estimated) on token generation; the estimate follows the measured 3090 Ti number (42.0 → 60.9 t/s at n-max 2). It costs ~0.6–2 GB extra VRAM and does not change output quality, and it only applies to MTP-capable models — Llama-class models are unaffected. Details and the tuning rules: MTP guide →

Expected performance (Q4_K_M, single GPU)

ModelSize on GPUToken genToken gen (MTP est.)Prompt proc.Fits?
8B (Llama 3.1 8B, Mistral)~4.9 GB~99–130 t/s~144–214 t/s~1200–1500 t/s✅ Q8_0 with big ctx
13B Q4_K_M~8.5 GB~58–73 t/s~84–120 t/s~800–1000 t/s✅ 8K–16K ctx
13B Q6_K~10.6 GB~47–61 t/s~69–101 t/s~750 t/s✅ 4K–8K ctx
20B+ dense~13 GB———❌ just 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 →

Estimates, full GPU offload, ~8K context.

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

QuantGGUF size1× 3080 Ti (12 GB)2× 3080 Ti (24 GB)
Q4_K_M~19 GB❌ ~7 GB over✅ ~26–30 t/s, 8–16K ctx
Q5_K_M~22 GB❌⚠️ ~20–22 t/s, 4–8K ctx
Q6_K~25 GB❌❌ ~1 GB over
Q8_0~33 GB❌❌

The single card is 12 GB: 27B doesn't fit, same wall as the 3060 12GB (but that pair runs the same 27B Q4 at 2× the speed). The dual build is the fastest 24 GB 27B rig below the 3090s: ~26 t/s on Q4_K_M is a genuinely pleasant chat speed, and Q5_K_M is usable with a short context. Q6/Q8 want 36 GB+, which is a 3090 mixed-build conversation (3090 + 3080 Ti = 36 GB, both quants fit).

Practical tips

Multi-card: 2×, 3×, 4×

Single-card numbers above. 960 GB/s per tile makes this the fastest PCIe 30-series tile — no NVLink, so the ~30% split tax still applies.

BuildGPU powerVRAM13B Q427B Q4_K_M27B Q5_K_M27B Q6_K27B Q8_0
2× 3080 Ti700 W24 GB~65 t/s✅ ~25–28 t/s⚠️ ~20–22 t/s, 4–8K❌ ~1 GB over❌
3× 3080 Ti1050 W36 GB~78 t/s~33 t/s~28 t/s~25–27 t/s⚠️ ~18–20 t/s, 8K
4× 3080 Ti1400 W48 GB~100 t/s~38 t/s~33 t/s~30–32 t/s~23–25 t/s
4× 3080 Ti · 70B1400 W48 GB—70B Q4_K_M at ~20–23 t/s — strong, but 2× 3090 with NVLink beats it for 200 W less

3× (36 GB) is the 27B-Q6 point for a PCIe-only money: ~26 t/s, a quant that a 24 GB box can't even hold. 4× (48 GB) is a full 70B-Q4 / 27B-Q8 rig — the strongest all-PCIe 48 GB build in the RTX 30 Series, at the price of 1.4 kW and a workstation board. If your budget touches 3090 prices, the mixed 3090+3080 Ti (36 GB) and 2× 3090 (48 GB) builds leapfrog the 3×/4× Tis on power and interconnect.

Offloading (CPU RAM)

When a model doesn't fit, -ngl N keeps the last layers on the CPU instead. The rule to internalize: offloaded layers run at CPU speed, not a percentage of GPU speed. A 27B model that's half offloaded is not 50% of GPU speed — it's ~3–5 t/s total on a modern 8-core. Practical patterns: drop just the last 2–4 layers to the CPU to reclaim ~0.5–1 GB of VRAM (nearly free); keep MoE experts on CPU with --n-cpu-moe; park the output embedding with -ot output=CPU to save another ~0.5 GB on big models. Budget 32 GB of system RAM for 27B-class offload, 64 GB for 70B. Never offload the KV cache — the conversation gets unusably slow. Offload is only interesting on the 24 GB pair, for the 1-GB Q6 gap: the IQ6_XS imatrix quant (~24 GB) fits without offloading and is the better fix.

3-card / 4-card examples llama-server -m 27b-q6_k.gguf -ngl 99 -sm layer -c 16384 --tensor-split 1,1,1
llama-server -m 70b-q4_k_m.gguf -ngl 99 -sm layer -c 8192 --tensor-split 1,1,1,1

Recommended llama.cpp command

llama-server -m llama-3-13b-q4_k_m.gguf -ngl 99 -c 16384 -b 2048 -ub 2048 --host 127.0.0.1 --port 8080

Verdict

The best single-card 13B experience under 24 GB: near-3090 bandwidth, honest 12 GB, and strong prompt processing. It loses to the 3090 on capacity (and price, if you can find either), but as a fast 8–13B machine — or a tile in a mixed multi-GPU build — the 3080 Ti has no equal below the 3090 line.

← RTX 3080 12 GB next: RTX 3090 →