Open-Assistant Llama2 70B SFT v10 TPS calculator

Open weights 70B parameters August 2023

Each card below is assessed against this model at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from the card's memory bandwidth and the size of the model once compressed.

Calculated for this model

61 cards that can run it

818 cards we hold specifications for

Smallest card that fits

A100 PCIe 40 GB

40 GB · IQ4_XS · 23.2 tok/s

Fastest card

B200

48.4 tok/s · 180 GB

Which GPUs can run Open-Assistant Llama2 70B SFT v10?

Set the inputs, read the answer

Context length tokens

A longer conversation needs more memory, which can push this model off smaller cards.

Minimum quality

Hides cards that would only fit the model by compressing it below this point.

Search cards

Card memory

Also show cards that cannot run it

61 cards match

Calculating

					Needs	Quantisation	Fit
48.4 tok/s 41–58	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	72.5 GB	Q8_0	Comfortable
48.4 tok/s 41–58	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	72.5 GB	Q8_0	Comfortable
38.7 tok/s 23–62 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	72.5 GB	Q8_0	Comfortable
38.7 tok/s 23–62 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	72.5 GB	Q8_0	Comfortable
30.9 tok/s 19–49 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	72.5 GB	Q8_0	Comfortable
29.6 tok/s 25–36	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	72.5 GB	Q8_0	Comfortable
29.6 tok/s 25–36	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	72.5 GB	Q8_0	Comfortable
29.5 tok/s 25–35	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	56.2 GB	Q6_K	Comfortable
29.5 tok/s 25–35	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	56.2 GB	Q6_K	Comfortable
28.3 tok/s 17–45 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	72.5 GB	Q8_0	Comfortable
26.1 tok/s 22–31	GRID A100B NVIDIA	48 GB	1,870 GB/s	May 2020	39.9 GB	Q4_K_M	Tight
25.1 tok/s 15–40 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	72.5 GB	Q8_0	Comfortable
25.1 tok/s 15–40 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	72.5 GB	Q8_0	Comfortable
25.1 tok/s 15–40 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	72.5 GB	Q8_0	Comfortable
23.8 tok/s 20–29	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	72.5 GB	Q8_0	Tight
23.2 tok/s 20–28	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	35.8 GB	IQ4_XS	Tight
23.2 tok/s 20–28	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	35.8 GB	IQ4_XS	Tight
23.2 tok/s 20–28	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	35.8 GB	IQ4_XS	Tight
20.3 tok/s 17–24	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	72.5 GB	Q8_0	Tight
20.3 tok/s 17–24	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	72.5 GB	Q8_0	Tight
20.3 tok/s 17–24	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	72.5 GB	Q8_0	Tight
18.7 tok/s 16–22	RTX PRO 5000 Blackwell NVIDIA	48 GB	1,340 GB/s	Mar 2025	39.9 GB	Q4_K_M	Tight
17.9 tok/s 15–22	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	56.2 GB	Q6_K	Comfortable
17.9 tok/s 15–22	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	56.2 GB	Q6_K	Comfortable
17.9 tok/s 15–22	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	56.2 GB	Q6_K	Comfortable

Speeds are estimates for a single request — one conversation at a time — calculated from memory bandwidth, model size and quantisation. Real throughput varies with the inference runtime and its version. Figures published by hardware vendors measure many simultaneous requests and are much higher.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Published: 25 August 2023
Authors: OpenAssistant

What it does

The problem areas the model was built for. A model can carry several of each.

Domain: Language
Task: Chat, Language modeling/generation
Base model: Llama 2-70B

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters: 70B
Training data: tokens

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Fine-tuning compute: 1.7 × 10²⁰ FLOP

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights: Open — downloadable
Model access: Open weights (restricted use)
Training code: Open (restricted use)

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence: Confident

Sources

Where this record came from and when it was last checked.

Reference: Open-Assistant Llama2 70B SFT v10
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Open-Assistant Llama2 70B SFT v10

Ranked by estimated tokens per second, newest card first where speeds tie. Because generation is bound by memory bandwidth, this ordering follows bandwidth rather than any gaming benchmark.

The smallest GPUs that still run Open-Assistant Llama2 70B SFT v10

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

What the numbers mean

What you need to run it

Minimum card

A100 PCIe 40 GB

Memory needed

35.8 GB

Fastest

48.4 tok/s

Open-Assistant Llama2 70B SFT v10 sits at 70B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 61 of the cards we track can hold it.

The least hardware that works is a A100 PCIe 40 GB. Its 40 GB is enough at IQ4_XS compression, giving roughly 23.2 tokens per second.

A B200 is the fastest we calculate for it: about 48.4 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

Open-Assistant Llama2 70B SFT v10 was published by its authors, in August 2023.

It works in Language, and is recorded as doing chat, Language modeling/generation.

It is derived from Llama 2-70B rather than trained from scratch, which is the usual way a specialised model is produced.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all.

Understanding the speeds

Across every card that can run it, the middle of the range is about 17.1 tokens per second, and 49 of them clear the ten tokens per second that roughly matches reading speed.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

Its attention layout is on file, so the memory figures are computed exactly rather than approximated.

Step by step

How to choose a GPU for Open-Assistant Llama2 70B SFT v10

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

The table lists every card that can hold Open-Assistant Llama2 70B SFT v10 — around 35.8 GB at IQ4_XS. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Open-Assistant Llama2 70B SFT v10 stops fitting a card that seemed fine.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of Open-Assistant Llama2 70B SFT v10 — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

Ranking by tokens per second for Open-Assistant Llama2 70B SFT v10 follows memory bandwidth, not core counts, which is why the B200 tops it at 48.4 tok/s.
05

Check the fit verdict before buying

Tight means Open-Assistant Llama2 70B SFT v10 loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
06

Open the card you have settled on

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Open-Assistant Llama2 70B SFT v10.

Answers

Open-Assistant Llama2 70B SFT v10 — common questions

What is Open-Assistant Llama2 70B SFT v10 used for?

Open-Assistant Llama2 70B SFT v10 works in Language, and is recorded as handling chat, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Open-Assistant Llama2 70B SFT v10?

The weights for Open-Assistant Llama2 70B SFT v10 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run Open-Assistant Llama2 70B SFT v10 if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down — the nearest miss we calculate is short by 11.1 GB. Our figures for Open-Assistant Llama2 70B SFT v10 assume it is fully resident.

Would two GPUs run Open-Assistant Llama2 70B SFT v10 faster?

Capacity adds across cards; throughput does not. Since 61 of the cards we track already hold Open-Assistant Llama2 70B SFT v10 on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Open-Assistant Llama2 70B SFT v10?

Each card is shown running the least-compressed copy it can hold, and Open-Assistant Llama2 70B SFT v10 appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Open-Assistant Llama2 70B SFT v10 speed estimates?

These are estimates with real error bars. The fastest result here, 41–58 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run Open-Assistant Llama2 70B SFT v10?

The smallest card in our catalogue that holds Open-Assistant Llama2 70B SFT v10 is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at IQ4_XS using about 35.8 GB, and produces roughly 23.2 tokens per second. 61 cards in total can run it.

How fast is Open-Assistant Llama2 70B SFT v10 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 48.4 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 49 of the cards that can run Open-Assistant Llama2 70B SFT v10 clear that.

How much VRAM does Open-Assistant Llama2 70B SFT v10 need?

About 35.8 GB at IQ4_XS compression, which is what the smallest card that runs it uses. Less compression needs more: the figures in the memory column above are recalculated for each card, because each one holds the least-compressed version it can.

Is Open-Assistant Llama2 70B SFT v10 open source?

Its weights are published, so Open-Assistant Llama2 70B SFT v10 can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

How many parameters does Open-Assistant Llama2 70B SFT v10 have?

Open-Assistant Llama2 70B SFT v10 has 70B parameters. "This model is an Open-Assistant fine-tuning of Meta's Llama2 70B LLM" (https://huggingface.co/OpenAssistant/llama2-70b-oasst-sft-v10). That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

When was Open-Assistant Llama2 70B SFT v10 released?

Open-Assistant Llama2 70B SFT v10 was published in August 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.

All AI models