Tenstorrent Blackhole p150
VRAM
32 GB
Memory
GDDR6
Bandwidth
512 GB/s
FP16
332 TF
TDP
300 W
Memory and compute
Architecture and power
Notes
Open-source stack (TT-Metalium). 664 TFLOPS BLOCKFP8 / 332 BF16 per Tenstorrent; 120 Tensix cores (cards downgraded from 140 via firmware, Jan 2026). 4x QSFP-DD 800G ports pool memory across cards. $1,399 active or passive.
Models that may fit on Tenstorrent Blackhole p150
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
Frequently asked questions about Tenstorrent Blackhole p150
Answered from the entry's own figures: memory, which models fit, bandwidth, power and the card's class.
Tenstorrent Blackhole p150 has 32 GB of GDDR6 at 512 GB/s. At INT8 a model's weights take about one byte per parameter, so the card holds roughly a 25B-parameter model with room for context; larger models need several cards or a lower precision.
From the catalog's estimates at INT8, Qwen 2.5 14B Instruct, DeepSeek V2 Lite Chat, Llama Nemotron Embed VL 1B V2 and GLM Z1 9B 0414 fit on a single Tenstorrent Blackhole p150 with their default context. The list on this page shows the estimated memory each takes; the capacity planner sizes any model against this card for your own context length, batch size and request rate.
512 GB/s. Bandwidth bounds how fast a model generates tokens, because every token reads the whole set of weights and the KV cache from memory; at this rate a 25B model at INT8 could be read on the order of 20 times a second on one card, before batching and framework efficiency.
Tenstorrent Blackhole p150 has a TDP of 300 W, in the PCIe form factor. Budget the TDP per card plus host overhead when sizing a server's power and cooling.
Tenstorrent Blackhole p150 is a datacenter accelerator, meant for servers and multi-GPU serving, built on the Tenstorrent Blackhole architecture and released in 2024. It supports a multi-GPU interconnect, so a model larger than one card can be split across several.
Specifications from the manufacturer's published material; a figure that is not published is shown as such, and a derived one is explained in the notes.
Added Jul 30, 2026 · Last updated Jul 30, 2026
Explore more
Companion tools that draw on the same catalog and routing engine.
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.