NVIDIA · Blackwell · 16 GB · Qwen3.8 27B · Q4_K_M: ~12 tok/s with RAM offload
NVIDIA GeForce RTX 5070 Ti 16GB
Twice the bandwidth of a 5060 Ti with the same 16 GB, so whatever fits runs fast. The 16 GB is the catch: 14B models at Q6, or a 35B-A3B mixture-of-experts model with part of it in system RAM.
Lowest price right now
$1,007.98
eBay · $994.99 + $12.99 shipping · $62 per GB · observed 2026-10-18 02:55 UTC
Buy the cheapest on eBay, $1,007.98
$994.99 + $12.99 shipping · New · newegg 1,084,675 · 99.6%
Price alert
One email per move, item plus shipping. Clear the price to hear about any drop. Manage alerts.
Price history
Tracking started today. The chart appears once there is a second day of data.
Where to buy
| Vendor | Price | Condition | Observed | |
|---|---|---|---|---|
| eBay cheapest active listing |
$1,007.98 $994.99 + $12.99 shipping |
new and used | 2026-10-18 02:55 UTC | Go to eBay |
On eBay now
92 listings passed our filters at the last check. Cheapest delivered first. Seller reputation is feedback count and positive rate.
-
$1,007.98$994.99 + $12.99 shipping -
$1,049.98$1,036.99 + $12.99 shipping -
$1,050plus shipping -
$1,109.99free shipping -
$1,150plus shipping -
$1,159.90free shipping
What it runs
For each model, grouped by vendor with the newest first: the largest quant that fits with 8K of context and the estimated speed for one user, at 8K and at 32K of context. On a card, a model too big for its memory can still run with part of the weights in system RAM; we assume 64 GB, and the speed shown accounts for it. The model you picked on the ladder is highlighted. Estimates from the spec sheet, not measurements: see how we estimate.
| Model | Quant | Needs at 8K | Fit | Max context | Decode at 8K | At 32K | Prefill tok/s |
|---|---|---|---|---|---|---|---|
| DeepSeek | |||||||
| DeepSeek V4.1 Flash 552B-A16B Sep 2026 | Q4_K_M | 338 GB | does not fit | ||||
| DeepSeek V4 Flash 284B-A13B Jul 2026 | Q4_K_M | 175 GB | does not fit | ||||
| DeepSeek V3.1 671B-A37B Aug 2025 | Q4_K_M | 411 GB | does not fit | ||||
| Gemma | |||||||
| Gemma 4 12B May 2026 | Q8_0 | 14 GB | fits | 109K | ~45 | ~44 | ~1,300 |
| Gemma 4 31B Mar 2026 | IQ2_M | 13 GB | fits | 48K | ~52 | ~44 | ~500 |
| Gemma 4 26B-A4B Mar 2026 | Q3_K_M | 14 GB | fits | 102K | ~140 | ~130 | ~4,100 |
| Gemma 3 27B Mar 2025 | Q3_K_M | 16 GB | fits | 12K | ~41 | ~560 | |
| GLM | |||||||
| GLM-5.3 753B-A40B Aug 2026 | Q4_K_M | 462 GB | does not fit | ||||
| GLM-5.3 Flash 320B-A18B Aug 2026 | Q4_K_M | 197 GB | does not fit | ||||
| GLM-4.6 355B-A32B Sep 2025 | Q4_K_M | 221 GB | does not fit | ||||
| GLM-4.5 Air 106B-A12B Jul 2025 | Q4_K_M | 68 GB | runs with 52 GB in system RAM | ~6.5 | ~640 | ||
| gpt-oss | |||||||
| gpt-oss-120b Aug 2025 | Q3_K_M | 59 GB | runs with 44 GB in system RAM | ~19 | ~18 | ~1,500 | |
| gpt-oss-20b Aug 2025 | Q4_K_M | 15 GB | fits | 33K | ~130 | ~100 | ~4,300 |
| Llama | |||||||
| Llama 4 Scout 109B-A17B Apr 2025 | Q4_K_M | 70 GB | runs with 54 GB in system RAM | ~4.6 | ~450 | ||
| Llama 3.3 70B Dec 2024 | Q4_K_M | 47 GB | runs with 32 GB in system RAM | ~1.3 | ~1.0 | ~110 | |
| Llama 3.1 8B Jul 2024 | Q8_0 | 11 GB | fits | 44K | ~61 | ~46 | ~1,900 |
| MiMo | |||||||
| MiMo V2.6 Pro 1.02T-A42B Sep 2026 | Q4_K_M | 624 GB | does not fit | ||||
| MiMo V2.6 Flash 309B-A15B Sep 2026 | Q4_K_M | 190 GB | does not fit | ||||
| Mistral | |||||||
| Mistral Medium 3.5 128B Mar 2026 | Q3_K_M | 67 GB | runs with 52 GB in system RAM | ~0.8 | ~60 | ||
| Mistral Small 4 119B-A6.5B Mar 2026 | Q3_K_M | 65 GB | runs with 49 GB in system RAM | ~13 | ~1,200 | ||
| Mistral Small 3.2 24B Jun 2025 | Q3_K_M | 15 GB | fits | 16K | ~44 | ~640 | |
| Nemotron | |||||||
| Nemotron 3.5 Lightning 30B-A3B Aug 2026 | IQ2_M | 12 GB | fits | 128K+ | ~180 | ~170 | ~4,400 |
| Qwen | |||||||
| Qwen3.8 Flash-Next 125B-A6B Aug 2026 | Q3_K_M | 63 GB | runs with 47 GB in system RAM | ~17 | ~16 | ~1,300 | |
| Qwen3.8 27B Aug 2026 (your pick) | Q3_K_M | 15 GB | fits | 18K | ~42 | ~570 | |
| Qwen3.6 27B Apr 2026 | Q3_K_M | 15 GB | fits | 18K | ~42 | ~570 | |
| Qwen3.6 35B-A3B Apr 2026 | IQ2_M | 14 GB | fits | 123K | ~180 | ~160 | ~5,100 |
| Qwen3.5 9B Feb 2026 | Q8_0 | 11 GB | fits | 128K+ | ~59 | ~55 | ~1,700 |
| Qwen3 Coder 480B-A35B Jul 2025 | Q4_K_M | 296 GB | does not fit | ||||
| Qwen3 235B-A22B Jul 2025 | Q4_K_M | 146 GB | does not fit | ||||
| Qwen3 32B Apr 2025 | IQ2_M | 15 GB | fits | 12K | ~44 | ~470 | |
Specifications
- Memory
- 16 GB GDDR7
- Memory bandwidth
- 896 GB/s
- Bus width
- 256-bit
- Shader cores
- 8,960
- Tensor cores
- 280
- FP32
- 43.9 TFLOPS
- FP16 (dense)
- 88 TFLOPS
- FP8 (dense)
- 176 TFLOPS
- Power
- 300 W
- Form factor
- Dual or triple slot, full height
- Interface
- PCIe 5.0 x16
- Architecture
- Blackwell
- Launched
- 2025
- MSRP
- $749
Source: manufacturer specifications.