SaulLM 7B
Equall.ai · dense · 7.2B parameters · 8,192 context
Parameters
7.2B
Context Window
8K tokens
Architecture
Dense
Best GPU
A10G
Intelligence Brief
SaulLM 7B is a 7.2B parameter DENSE model from Equall.ai, featuring Grouped Query Attention (GQA) with 32 layers and 4,096 hidden dimensions. With a 8,192 token context window, it supports general text generation. For self-hosted inference, A10G delivers optimal throughput at $285/month.
Architecture Details
Memory Requirements
BF16 Weights
14.4 GB
FP8 Weights
7.2 GB
INT4 Weights
3.6 GB
GPU Compatibility Matrix
SaulLM 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
225.0 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
349.9 tok/s
Latency (ITL)
2.9ms
Est. TTFT
0ms
Cost/Month
$332
Cost/M Tokens
$0.36
BF16 · 1 GPU · vllm
100/100
score
Throughput
378.0 tok/s
Latency (ITL)
2.6ms
Est. TTFT
0ms
Cost/Month
$370
Cost/M Tokens
$0.37
Deployment Options
API Deployment
No API pricing available
Single GPU
A10G
$285/mo
Min VRAM: 7 GB
Multi-GPU
RTX 3080 x2
441.4 tok/s
TP· $266/mo
API Pricing Comparison
No API pricing data available for this model.
Performance Estimates
Throughput by GPU
VRAM Breakdown (A10G, BF16)
Precision Impact
bf16
14.4 GB
weights/GPU
~225.0 tok/s
fp8
7.2 GB
weights/GPU
int4
3.6 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy SaulLM 7B
Self-Hosted Infrastructure
Similar Models
BioMistral 7B
7.2B params · dense
Quality: 50
FinGPT 7B
7.2B params · dense
Quality: 50
DeepSeek Math 7B
7.24B params · dense
Quality: 50
Prometheus 2 7B
7.24B params · dense
Quality: 50
NV EmbedQA Mistral 7B
7.24B params · dense
Quality: 50
from $0.01/M
Frequently Asked Questions
How much VRAM does SaulLM 7B need for inference?
SaulLM 7B requires approximately 14.4 GB of VRAM at BF16 precision, 7.2 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 SaulLM 7B?
The top recommended GPU for SaulLM 7B is the A10G using BF16 precision. It achieves approximately 225.0 tokens/sec at an estimated cost of $285/month ($0.48/M tokens). Score: 100/100.
How much does SaulLM 7B inference cost?
SaulLM 7B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.