Skip to content
Local AI Wizard
Your machine
Theme

Local text models

Chat and writing · Chat, writing, code, translation, classification and extraction.

Quality · Overall

LiveBench 0–100 · higher is better

  • Color = publisher
  • Memory under review

Source: LiveBench · release of Jun 25, 2026 · checked Oct 18, 2026 · 37 open models without a score in this release are not drawn (no score ≠ 0)

Top score

DeepSeek V4.1 Flash · max: 81.1 on LiveBench Overall

Lightest scored

Smaug Mini: ~21 GB Q4, model only, 76.9

Licenses

13 of 23 scored open models use MIT or Apache 2.0

Catalog

768 more repositories without a LiveBench score (no score ≠ 0)

Choose your machine and the charts and tables mark what fits in its memory.

23 scored models · LiveBench Jun 25, 2026 

Text models
DeepSeek V4.1 Flash · maxDeepSeek · MIT81.1Not publishedMemory estimate under reviewMIT
Smaug AgenticAbacus AI · Publisher terms: Kimi K379.52,800~2.1 TBPublisher terms: Kimi K3
Kimi K3Moonshot AI · Publisher terms: Kimi K379.22,800~2.1 TBPublisher terms: Kimi K3
Qwen3.8 MaxAlibaba · Publisher terms: Qwen3.8 Max78.52,400~1.8 TBPublisher terms: Qwen3.8 Max
DeepSeek V4 Pro · 0813DeepSeek · MIT77.41,600~1.2 TBMIT
Smaug FlashAbacus AI · MIT77.4Not publishedMemory estimate under reviewMIT
Smaug MiniAbacus AI · Apache 2.076.927~21 GBApache 2.0
DeepSeek V4 Flash Vision · expDeepSeek · MIT76.8Not publishedMemory estimate under reviewMIT
Qwen3.8 Flash NextAlibaba · Publisher terms: Qwen Community 1.076.2Not publishedMemory estimate under reviewPublisher terms: Qwen Community 1.0
GLM-5.3Z.ai · Publisher terms: GLM-5.376.1744~558 GBPublisher terms: GLM-5.3
Qwen3.8 27BAlibaba · Apache 2.075.327~21 GBApache 2.0
DeepSeek V4 Flash · 0731DeepSeek · MIT74.2304~228 GBMIT
GLM-5.2Z.ai · MIT73.2744~558 GBMIT
Inkling · xhighThinking Machines · Apache 2.071.9975~732 GBApache 2.0
GLM-5.3 FlashZ.ai · MIT71.6320~240 GBMIT
DeepSeek V4 ProDeepSeek · MIT71.61,600~1.2 TBMIT
Kimi K2.6 · thinkingMoonshot AI · Publisher terms: Modified MIT70.51,000~750 GBPublisher terms: Modified MIT
Kimi K2.7 CodeMoonshot AI · Publisher terms: Modified MIT68.41,000~750 GBPublisher terms: Modified MIT
Nemotron 3 Ultra 550B A55BNVIDIA · OpenMDW 1.167.4550~413 GBOpenMDW 1.1
MiniMax M3MiniMax · Publisher terms: MiniMax Community67.3428~321 GBPublisher terms: MiniMax Community
DeepSeek V4 FlashDeepSeek · MIT65.5284~213 GBMIT
Qwen3.6 27BAlibaba · Apache 2.064.027~21 GBApache 2.0
Nemotron 3.5 Lightning 30B A3BNVIDIA · OpenMDW 1.144.530~23 GBOpenMDW 1.1