Model
Model explorer
Qwen-7B
OPENAlibaba · Qwen family · released Aug 3, 2023
First open Qwen release: 7B dense on 2.4T tokens; native 8K context extendable to 32K via NTK-aware interpolation and LogN attention scaling.
ReasoningCodingVisionFunction callingTool useAgentic
137.5
Elo · rank #374
Parameters
7B
Active params
7B (dense)
Context
32K tokens
Architecture
Dense decoder-only transformer (RoPE, SwiGLU, RMSNorm, untied embeddings)
License
Tongyi Qianwen LICENSE AGREEMENT (custom, free commercial use below usage threshold)
Languages
—
API price (in/out)
No hosted API
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
best: ERNIE 4.5 300B-A47B · 94.3%
best: Qwen3.6-Plus · 93.3%
best: Doubao-1.5-Pro · 90.9%
best: Llama 3.1 405B · 96.8%
best: Claude Opus 4.5 · 99.4%
best: GPT-5 · 99.4%
best: Llama-3.3-Nemotron-Super-49B v1 (Reasoning On) · 91.3%
best: OpenAI o3 · 92.9%
Run it locally
VRAM @ Q4
4.5 GB
VRAM @ FP16
14 GB
Fits on (Q4)
RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB
Throughput data unavailable.
Quantizations
GPTQ Int4 · GPTQ Int8 · GGUF
Qwen family
Elo progression across releases
Resources
API price weights · each benchmark row carries its own source badge (see methodology)