Qwen 2.5 14B
Alibaba · dense · 14.8B parameters · 131,072 context
Parameters
14.8B
Context Window
128K tokens
Architecture
Dense
Best GPU
A100 40GB SXM
Cheapest API
$0.30/M
Quality Score
76/100
Intelligence Brief
Qwen 2.5 14B is a 14.8B parameter DENSE model from Alibaba, featuring Grouped Query Attention (GQA) with 48 layers and 5,120 hidden dimensions. With a 131,072 token context window, it supports tools, structured output, code, math, multilingual. On standardized benchmarks, it achieves MMLU 79.9, HumanEval 50, GSM8K 87. The most cost-effective API deployment is via together at $0.30/M output tokens. For self-hosted inference, A100 40GB SXM delivers optimal throughput at $807/month.
Provider pricing
2 providers · canonical: alibaba| Provider | Input $/M | Output $/M ▲ | Notes |
|---|---|---|---|
| together | $0.300 | $0.300 | cheapest input · cheapest output |
| alibabacanonical | $0.400 | $0.400 | — |
Prices update via the nightly pricing cron + admin approvals at /admin/ingest-queue. The leaderboard's Input/Output cells show the canonical rate above; this table shows the full spread.
Recent changes
Loading…
Related models
5 suggestions- Qwen 2.5 32BQwen 2.5 · 32.5B$0.800/M out
- Qwen 2.5 3BQwen 2.5 · 3.09B$0.100/M out
- Qwen 2.5 Coder 32BQwen 2.5 · 32.5Bfree/M out
- Qwen 2.5 0.5BQwen 2.5 · 0.5B—
- Qwen 2.5 1.5BQwen 2.5 · 1.5B—
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
29.6 GB
FP8 Weights
14.8 GB
INT4 Weights
7.4 GB
GPU Compatibility Matrix
Qwen 2.5 14B is compatible with 82% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
95/100
score
Throughput
283.7 tok/s
Latency (ITL)
3.5ms
Est. TTFT
1ms
Cost/Month
$807
Cost/M Tokens
$1.08
BF16 · 1 GPU · vllm
95/100
score
Throughput
140.1 tok/s
Latency (ITL)
7.1ms
Est. TTFT
1ms
Cost/Month
$465
Cost/M Tokens
$1.26
BF16 · 1 GPU · vllm
95/100
score
Throughput
127.0 tok/s
Latency (ITL)
7.9ms
Est. TTFT
1ms
Cost/Month
$399
Cost/M Tokens
$1.19
Deployment Options
API Deployment
together
$0.30/M
output tokens
Single GPU
A100 40GB SXM
$807/mo
Min VRAM: 15 GB
Multi-GPU
RTX 3090 x2
283.9 tok/s
TP· $361/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| together | $0.30 | $0.30 | Cheapest |
| alibaba | $0.40 | $0.40 |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| togetherBest Value | $0.30 | $0.30 | $3 |
| alibaba | $0.40 | $0.40 | $4 |
Cost per 1,000 Requests
Short (500 tok)
$0.21
via together
Medium (2K tok)
$0.84
via together
Long (8K tok)
$3.00
via together
Performance Estimates
Throughput by GPU
VRAM Breakdown (A100 40GB SXM, BF16)
Precision Impact
bf16
29.6 GB
weights/GPU
~283.7 tok/s
fp8
14.8 GB
weights/GPU
int4
7.4 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Qwen 2.5 14B
Similar Models
Qwen 2.5 7B
7.6B params · dense
Quality: 70
from $0.00/M
Qwen 2.5 32B
32.5B params · dense
Quality: 73
from $0.80/M
Qwen 2.5 Coder 32B
32.5B params · dense
Quality: 80
from $0.00/M
DeepSeek R1 Distill 14B
14.8B params · dense
Quality: 88
from $0.30/M
Phi-4
14.7B params · dense
Quality: 73
from $0.14/M
Frequently Asked Questions
How much VRAM does Qwen 2.5 14B need for inference?
Qwen 2.5 14B requires approximately 29.6 GB of VRAM at BF16 precision, 14.8 GB at FP8, or 7.4 GB at INT4 quantization. Additional VRAM is needed for KV-cache (196608 bytes per token) and activations (~1.50 GB).
What is the best GPU for Qwen 2.5 14B?
The top recommended GPU for Qwen 2.5 14B is the A100 40GB SXM using BF16 precision. It achieves approximately 283.7 tokens/sec at an estimated cost of $807/month ($1.08/M tokens). Score: 95/100.
How much does Qwen 2.5 14B inference cost?
Qwen 2.5 14B API inference starts from $0.30/M input tokens and $0.30/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.