Datacenter GPUAMD

AMD Instinct MI210 64GB

Name: AMD Instinct MI210 64GB
Brand: AMD
SKU: mi210

Curated Aggregate·2024-09-303 workloads · 3 records

MyAI RatingNot scoredInsufficient comparison evidence

VRAM

64 GB

TDP

300 W

MSRP

$8.0k

Perf/W

0.09 tok/s/W

Cost/1K tok

$0.0030/k

Tested

2024-09-30

Quick answer

How many tokens per second does AMD Instinct MI210 64GB produce on Llama 3 70B Q4?

AMD Instinct MI210 64GB has a source-attributed result of 28.0 tok/s on Llama 3 70B Q4 (batch 1, 4096-token context, Q4_K_M; runtime not documented). This is a reference report, not an independently verified lab result. A 70B Q4_K_M artifact needs roughly 40GB for weights alone; smaller memory configurations require explicit offload or model splitting and do not establish full-GPU residency.

Verdict

AMD Instinct MI210 64GB with 64GB VRAM at 300W TDP, scored across 3 workloads with 3 benchmark records.

Reference workload

Llama 3 70B Q4

28 tok/s

Quantization

Q4_K_M

4K context · batch 1

LLM Inference Performance

Benchmarks (3 workloads)

Workload	Score	Quant	Context	σ	Status	Tested
Llama 3 70B Q4 llm	28.0tok/s	Q4_K_M	4K	,	Curated Aggregate	2024-09-30
Mistral 7B llm	105.0tok/s	Q4_K_M	4K	,	Curated Aggregate	2024-04-14
Phi-3 Mini llm	175.0tok/s	Q4_K_M	4K	,	Curated Aggregate	2024-05-19

MyAI Score: not scored

There is insufficient comparable evidence to score AMD Instinct MI210 64GB. A score needs results for multiple devices with matching workload, runtime version, quantization, context and batch size.

Workload Fit

Planning estimates for 64GB: weights plus at least 2GB or 10% overhead. Actual KV cache depends on model, context and cache format; confirm the artifact before buying.

FP16

7-8B

Excellent

13-14B

Excellent

32B

Excellent

Won't fit

70B

Excellent

Won't fit

Reported batch-one examples

Llama 3 70B Q428 tok/s

Phi-3 Mini175 tok/s

Mistral 7B105 tok/s

Source

ROCm 5.7.

View source How we benchmark →

Public Trust Layer

Trust score

6/10

MyAI rating

Not scored

Runs

Not documented

Freshness

Stale

Source-linked row with explicit verification status.

Record date: 2024-09-30; 709 days old.

Open primary source

Enterprise buying note

Where to buy

Reseller compare

Retailer we'd check first

Amazon search plus reseller quotes

For datacenter and accelerator parts, Amazon is useful for spotting live listings, accessories, or used pulls, but serious procurement usually happens through integrators, brokers, or cloud partners.

Enterprise procurement, not retail

This silicon is typically acquired through an authorized OEM partner, system integrator, or hyperscaler reseller. For on-demand access, compare hourly rates at RunPod, Vast.ai, Lambda Labs, or your existing cloud provider before committing to capital expenditure.

+Use $8.0k only as a rough anchor. Enterprise street pricing moves with supply, warranty, and included accessories.
+Confirm cooling, power delivery, and return terms before you purchase. These parts often ship without consumer-friendly safeguards.
+If this is for production, compare against authorized reseller quotes before you commit.

There is insufficient comparable evidence for a purchase recommendation. Check model fit, software support and a current seller quote.

Affiliate note: we do not have a device-level ASIN yet, so this opens tagged Amazon search results for the exact product name.