E5 Mistral 7B
IntFloat · dense · 7.11B parameters · 32,768 context
Parameters
7.11B
Context Window
32K tokens
Architecture
Dense
Best GPU
A10G
Cheapest API
$0.02/M
Intelligence Brief
E5 Mistral 7B is a 7.11B parameter DENSE model from IntFloat, featuring Grouped Query Attention (GQA) with 32 layers and 4,096 hidden dimensions. With a 32,768 token context window, it supports multilingual. The most cost-effective API deployment is via together at $0.02/M output tokens. For self-hosted inference, A10G delivers optimal throughput at $285/month.
Architecture Details
Memory Requirements
BF16 Weights
14.2 GB
FP8 Weights
7.1 GB
INT4 Weights
3.6 GB
GPU Compatibility Matrix
E5 Mistral 7B is compatible with 95% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
227.8 tok/s
Latency (ITL)
4.4ms
Est. TTFT
1ms
Cost/Month
$285
Cost/M Tokens
$0.48
BF16 · 1 GPU · vllm
100/100
score
Throughput
354.3 tok/s
Latency (ITL)
2.8ms
Est. TTFT
0ms
Cost/Month
$332
Cost/M Tokens
$0.36
BF16 · 1 GPU · vllm
100/100
score
Throughput
382.8 tok/s
Latency (ITL)
2.6ms
Est. TTFT
0ms
Cost/Month
$370
Cost/M Tokens
$0.37
Deployment Options
API Deployment
together
$0.02/M
output tokens
Single GPU
A10G
$285/mo
Min VRAM: 7 GB
Multi-GPU
RTX 3080 x2
446.4 tok/s
TP· $266/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| together | $0.02 | $0.02 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| togetherBest Value | $0.02 | $0.02 | $0 |
Cost per 1,000 Requests
Short (500 tok)
$0.01
via together
Medium (2K tok)
$0.04
via together
Long (8K tok)
$0.16
via together
Performance Estimates
Throughput by GPU
VRAM Breakdown (A10G, BF16)
Precision Impact
bf16
14.2 GB
weights/GPU
~227.8 tok/s
fp8
7.1 GB
weights/GPU
int4
3.6 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy E5 Mistral 7B
Self-Hosted Infrastructure
Similar Models
BioMistral 7B
7.2B params · dense
Quality: 50
SaulLM 7B
7.2B params · dense
Quality: 50
FinGPT 7B
7.2B params · dense
Quality: 50
OLMo 2 7B
7B params · dense
Quality: 50
Command R 7B
7B params · dense
Quality: 68
from $0.15/M
Frequently Asked Questions
How much VRAM does E5 Mistral 7B need for inference?
E5 Mistral 7B requires approximately 14.2 GB of VRAM at BF16 precision, 7.1 GB at FP8, or 3.6 GB at INT4 quantization. Additional VRAM is needed for KV-cache (131072 bytes per token) and activations (~0.80 GB).
What is the best GPU for E5 Mistral 7B?
The top recommended GPU for E5 Mistral 7B is the A10G using BF16 precision. It achieves approximately 227.8 tokens/sec at an estimated cost of $285/month ($0.48/M tokens). Score: 100/100.
How much does E5 Mistral 7B inference cost?
E5 Mistral 7B API inference starts from $0.02/M input tokens and $0.02/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.