Updated minutes ago
Code Llama 34B
Meta · dense · 34B parameters · 100,000 context
Quality55.0
Architecture Details
TypeDENSE
Total Parameters34B
Active Parameters34B
Layers48
Hidden Dimension8,192
Attention Heads64
KV Heads8
Head Dimension128
Vocab Size32,016
Memory Requirements
BF16 Weights
68.0 GB
FP8 Weights
34.0 GB
INT4 Weights
17.0 GB
KV-Cache per Token196608 bytes
Activation Estimate2.00 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
H20optimal
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
984.2 tok/s
Cost/Month
$940
Cost/M Tokens
$0.36
B200 SXMoptimal
FP8 · 1 GPU · tensorrt-llm
98/100
score
Throughput
1.1K tok/s
Cost/Month
$4261
Cost/M Tokens
$1.54
H200 SXMoptimal
FP8 · 1 GPU · tensorrt-llm
95/100
score
Throughput
1.1K tok/s
Cost/Month
$2553
Cost/M Tokens
$0.93
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| together | $0.78 | $0.78 | Cheapest |
Quality Benchmarks
MMLU56.0
HumanEval48.8
GSM8K45.0
MT-Bench68.0
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✓ Math✗ Reasoning✗ Multilingual✗ Structured Output
Supported Frameworks
vllmsglangtgitensorrt-llmollama
Supported Precisions
BF16 (default)FP8INT4