Updated minutes ago
Codestral Mamba 7B
Mistral AI · hybrid · 7.3B parameters · 262,144 context
Quality50.0
Architecture Details
TypeHYBRID
Total Parameters7.3B
Active Parameters7.3B
Layers64
Hidden Dimension4,096
Attention Heads1
KV Heads1
Head Dimension4096
Vocab Size32,768
Memory Requirements
BF16 Weights
14.6 GB
FP8 Weights
7.3 GB
INT4 Weights
3.6 GB
KV-Cache per Token0 bytes
Activation Estimate1.00 GB
Fits on (single-node)
B200 SXM BF16B100 SXM BF16GB200 NVL72 (per GPU) BF16GB300 NVL72 (per GPU) BF16H200 SXM BF16H100 SXM BF16H100 PCIe BF16H100 NVL BF16
GPU Recommendations
A30optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
310.6 tok/s
Cost/Month
$332
Cost/M Tokens
$0.41
RTX 4090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
335.5 tok/s
Cost/Month
$370
Cost/M Tokens
$0.42
RTX 3090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
311.6 tok/s
Cost/Month
$180
Cost/M Tokens
$0.22
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| mistral | $0.20 | $0.60 | Cheapest |
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✓ Math✗ Reasoning✗ Multilingual✗ Structured Output
Supported Frameworks
vllmsglang
Supported Precisions
BF16 (default)FP8INT4