Parameters
27B
Context Length
262K
Modality
Multimodal
Auxiliary Parameters
450M
Architecture
Dense
KV Cache Rate
256 KB/tok
License
Apache 2.0
Release Date
5 Aug 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.50 · Output: $3.00
Precision
Context
Workload Memory: 17.07 GB
INT4 · 8K context
Base Weights: 12.57 GB
KV Cache: 2.00 GB
Runtime & Graphs: 2.50 GB
1x NVIDIA L4 24GB
17.1 / 21.6 GB usable
2x RTX 4090 24GB
17.1 / 43.2 GB usable · TP 2
Apple M4 24GB
17.1 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 5.8.0.dev0
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashAttention-3 |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
Rank
#50
| Benchmark | Score | Rank |
|---|---|---|
Agentic Coding | 0.61 | 11 |
Agentic Index | max 0.46 medium 0.44 low 0.39 Standard 0.22 | 27 28 44 77 |
Graduate-Level QA | 0.892 | 27 |
Data Analysis | 0.77 | 28 |
General | 0.75 | 33 |
Web Development | 1590 | 33 |
LiveBench Average | 0.75 | 34 |
Coding | 0.76 | 48 |
Mathematics | 0.86 | 48 |
Reasoning | 0.80 | 50 |
Coding Index | max 0.68 medium 0.56 low 0.58 Standard 0.45 | 52 75 70 98 |
Agent Arena | -4.76 | 57 |
General Text | 1434 | 92 |
Intelligence Index | max 0.20 medium 0.17 low 0.16 Standard 0.10 | 171 197 210 249 |
Overall Rank
#50
Coding Rank
#43
Qwen 3.8 27B is a 27-billion parameter dense foundation model by Alibaba that offers balanced efficiency and strong reasoning performance. It excels at multi-turn conversational tasks, programming, and long-context understanding.
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
24
Key-Value Heads
4
Attention Head Dimension
256
Position Embedding
ROPE
RoPE Theta
10,000,000
Linear Attention
Yes
Linear Attention Ratio
75.0%
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Base Precision
FP16
Auxiliary Parameters
450M
Hidden Dimension Size
5,120
Number of Layers
64
FFN Intermediate Size (Dense)
17,408
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
248,320
Alibaba's Qwen 3.8 generation represents the frontier hybrid Mixture-of-Experts architecture designed for coding, professional work, research, and long-horizon agentic tasks. It features a 2.4-trillion parameter architecture (95B active per token) combining Gated DeltaNet linear attention with standard Gated Attention, available both as open weights and as a hosted flagship service.