Models / Qwen3 4B

Qwen3 4B

edge
HuggingFace → HuggingBay → Alibaba → Find for my hardware

AI-generated content marks

This model embeds text watermarks in generated text and adds C2PA provenance metadata to supported files such as .png, .jpg, and .svg. Marks can be lost through editing, screenshots, or format conversion, so their absence does not prove a file is human-made.

Provider transparency docs →

coding reasoning chat
Parameters
4.0B
Context
32k
License
apache 2.0
Developer
Alibaba
Origin
🇨🇳 China
Released
Apr 2025

Scores

Coding
58
Reasoning
60
General
56

Related models

Qwen3.8-Omni-Flash
125.0B enthusiast no local build $0.15/M in Sep 14, 2026
Qwen3.8-Flash-Next
180.0B 6.0B active enthusiast 24GB min RAM Aug 26, 2026
Qwen3.8-27B
27.0B enthusiast 8GB min RAM Aug 5, 2026
Qwen3.8-Max
2400.0B 95.0B active premier no local build $2.00/M in Aug 3, 2026
Qwen3.6 35B A3B
35.0B 3.0B active enthusiast 20GB min RAM $0.05/M in Apr 22, 2026
Qwen3.6 27B
27.0B enthusiast 17GB min RAM $0.25/M in Nov 1, 2025
Qwen3 14B
14.7B consumer 9GB min RAM $0.10/M in Apr 28, 2025
Qwen3 235B A22B
235.0B 22.0B active workstation 68GB min RAM $0.46/M in Apr 28, 2025
Qwen3 30B A3B
30.5B 3.0B active enthusiast 16GB min RAM $0.12/M in Apr 28, 2025
Qwen3 32B
32.8B enthusiast 20GB min RAM $0.08/M in Apr 28, 2025
Qwen3 8B
8.2B consumer 5GB min RAM $0.12/M in Apr 28, 2025

Save your hardware and every model page answers the real question: will it run on your machine, and how fast?

Join free - save your rig →

Run it locally

Per-quant memory needs and a static "can you run it?" reference - no rig entry required

Q4_K_M
2.6GB 2.6GB min 3.9GB rec
Balanced - the usual local sweet spot

The reference hardware

Schematic of the 4x H100 80GB (320GB) reference rig - 320GB VRAM, 13400 GB/s aggregate bandwidth
Schematic of the NVIDIA DGX Station 748GB reference rig - 748GB unified memory, 8000 GB/s aggregate bandwidth
Schematic of the 8x RTX 3090 rack (192GB) reference rig - 192GB VRAM, 7489 GB/s aggregate bandwidth
Schematic of the 4x RTX 5090 (128GB) reference rig - 128GB VRAM, 7168 GB/s aggregate bandwidth
Schematic of the AMD Instinct MI300X (192GB) reference rig - 192GB VRAM, 5324 GB/s aggregate bandwidth
Schematic of the 4x RTX 4090 (96GB) reference rig - 96GB VRAM, 4032 GB/s aggregate bandwidth
Schematic of the 2x RTX 5090 (64GB) reference rig - 64GB VRAM, 3584 GB/s aggregate bandwidth
Schematic of the 2x RTX 3090 (48GB) reference rig - 48GB VRAM, 1872 GB/s aggregate bandwidth
Schematic of the Single RTX 5090 (32GB) reference rig - 32GB VRAM, 1792 GB/s aggregate bandwidth
Schematic of the RTX PRO 6000 Blackwell (96GB) reference rig - 96GB VRAM, 1792 GB/s aggregate bandwidth
Schematic of the Mac Studio M4 Ultra 192GB reference rig - 192GB unified memory, 1092 GB/s aggregate bandwidth
Schematic of the Mac Studio M4 Ultra 512GB reference rig - 512GB unified memory, 1092 GB/s aggregate bandwidth
Schematic of the Single RTX 4090 (24GB) reference rig - 24GB VRAM, 1008 GB/s aggregate bandwidth
Schematic of the MacBook Pro M5 Max 128GB reference rig - 128GB unified memory, 614 GB/s aggregate bandwidth
Schematic of the Single GTX 1080 Ti (11GB) reference rig - 11GB VRAM, 484 GB/s aggregate bandwidth
Schematic of the Dual EPYC 9004 + 768GB DDR5-4800 reference rig - 768GB unified memory, 460 GB/s aggregate bandwidth
Schematic of the DGX Spark 128GB unified reference rig - 128GB unified memory, 273 GB/s aggregate bandwidth
Schematic of the Ryzen AI Max+ 395 128GB reference rig - 128GB unified memory, 256 GB/s aggregate bandwidth
Schematic of the Jetson AGX Orin 64GB reference rig - 64GB unified memory, 204 GB/s aggregate bandwidth
Schematic of the Epyc + 512GB DDR4-3200 + 2x RTX 3090 reference rig - 560GB unified memory, 204 GB/s aggregate bandwidth
Schematic of the Epyc + 512GB DDR4-2400 + 2x RTX 3090 reference rig - 560GB unified memory, 153 GB/s aggregate bandwidth
Schematic of the NVIDIA Jetson Orin NX 16GB reference rig - 16GB unified memory, 102 GB/s aggregate bandwidth

22 reference configs, drawn in-house. Scroll for more.

Can you run it? - reference rigs

Rig Q4_K_M
4x H100 80GB (320GB) fast 1966.4t/s
NVIDIA DGX Station 748GB fast 1174.0t/s
8x RTX 3090 rack (192GB) fast 1099.1t/s
4x RTX 5090 (128GB) fast 1051.9t/s
AMD Instinct MI300X (192GB) fast 781.4t/s
4x RTX 4090 (96GB) fast 591.7t/s
2x RTX 5090 (64GB) fast 525.9t/s
2x RTX 3090 (48GB) fast 274.8t/s
Single RTX 5090 (32GB) fast 263.0t/s
RTX PRO 6000 Blackwell (96GB) fast 263.0t/s
Mac Studio M4 Ultra 192GB fast 174.8t/s
Mac Studio M4 Ultra 512GB fast 174.8t/s
Single RTX 4090 (24GB) fast 147.9t/s
MacBook Pro M5 Max 128GB fast 98.3t/s
Single GTX 1080 Ti (11GB) fast 71.0t/s
Dual EPYC 9004 + 768GB DDR5-4800 fast 67.6t/s
DGX Spark 128GB unified fast 40.1t/s
Ryzen AI Max+ 395 128GB fast 37.6t/s
Jetson AGX Orin 64GB fast 30.1t/s
Epyc + 512GB DDR4-3200 + 2x RTX 3090 fast 30.1t/s
Epyc + 512GB DDR4-2400 + 2x RTX 3090 fast 22.5t/s
NVIDIA Jetson Orin NX 16GB ok 15.0t/s

Fit tiers use the same will-it-run logic as the rig finder. For comfortable fits, the badge reflects decode speed: fast >=20 t/s, ok 8-20 t/s, slow <8 t/s. t/s is a bandwidth estimate, not a measured benchmark.

Download options

Q4_K_M official -5% vs fp16
2.6GB dl 2.6GB min 3.9GB rec
REC RAM vs largest quant

Or run it in the cloud

No per-token API provider pricing tracked for Qwen3 4B yet. For flagship list prices, see the calculator.

See who runs Alibaba in production →

PRICE HISTORY

Inference cost over time

Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.

Loading price history...