Frontier zone · Model releases

The frontier of open-weight model releases

Open-weight model releases tracked by RunLocalAI — recent additions, rising families, distill chains, multimodal and reasoning waves. Each card links into the catalog with authority badges (L1.25 enriched · benchmark-backed · verdict) so you can scan editorial coverage at a glance.

By Fredoline Eruo · Refreshed continuously from catalog seed
Filter

Filtered results (22)

Models matching your filters. Clear filters by clicking “Any” on each row above, or remove individual filters via the URL.

Qwen 3.6 35B-A3B (MTP)

Alibaba / Qwen team · 2026-05-11
35B/3B-Aworkstation

high-throughput MoE inference at workstation tier

Verdict

Qwen 3.6 27B (MTP)

Alibaba / Qwen team · 2026-05-11
27Bworkstation

dense workstation model with throughput-acceleration

Verdict

Qwen 3 Coder 32B

Alibaba · 2025-11-20
32Bworkstation

coding-specialized agent workloads

Verdict

Qwen 3 7B

Alibaba · 2025-09-15
7Bconsumer

consumer-tier reasoning on 8GB+ GPUs

Verdict

Qwen 3 Embedding 8B

Alibaba · 2025-06-05
8Bconsumer

permissively-licensed embeddings at 8B

Verdict

Qwen 3 30B-A3B

Alibaba · 2025-04-29
30Bworkstation

workstation MoE — 3B active, 30B total

Verdict

Qwen 3 8B

Alibaba · 2025-04-29
8Bconsumer

consumer-tier reasoning toggle

Verdict

Qwen 2.5-VL 72B

Alibaba · 2025-03-10
72Bdatacenter

frontier-tier multimodal serving

VerdictMultimodal

Qwen 2.5-VL 7B

Alibaba · 2025-03-10
7Bconsumer

consumer-tier OCR + image Q&A

VerdictMultimodal

QwQ 32B Preview

Alibaba · 2024-11-27
32Bworkstation

workstation-tier reasoning — Qwen team alternative to R1

Verdict

Qwen 2.5 Coder 14B Instruct

Alibaba · 2024-11-12
14Bconsumer

16GB-VRAM coding

BenchmarkVerdict

Qwen 2.5 Coder 7B Instruct

Alibaba · 2024-11-12
7Bconsumer

consumer-tier coding at 8GB VRAM

Verdict

Qwen 2.5 Math 72B

Alibaba · 2024-09-19
72Bdatacenter

datacenter-tier math specialist

Verdict

Qwen 2.5 72B Instruct

Alibaba · 2024-09-19
72Bdatacenter

production multilingual at 70B-class

Verdict

Qwen 2.5 32B Instruct

Alibaba · 2024-09-19
32Bworkstation

workstation-tier multilingual general chat

Verdict

Qwen 2.5 14B Instruct

Alibaba · 2024-09-19
14Bconsumer

16GB-VRAM general chat with multilingual depth

Verdict

Qwen 2.5 Math 7B

Alibaba · 2024-09-19
7Bconsumer

consumer-tier math problem solving

Verdict

Qwen 2.5 7B Instruct

Alibaba · 2024-09-19
7Bconsumer

consumer-tier multilingual chat

BenchmarkVerdict

Qwen 2-VL 7B

Alibaba · 2024-08-29
7Bconsumer

consumer-tier multimodal — pre-2.5-VL baseline

VerdictMultimodal

CodeQwen 1.5 7B

Alibaba · 2024-04-16
7Bconsumer

historical reference — Qwen 2.5 Coder 7B is the modern pick

Verdict

Qwen3 Swallow 32B RL v0.2

tokyotech-llm
32B

Japanese-English reasoning tasks: math, coding, structured analysis

Verdict

Qwen3.5 9B Thai Law Base

Phonsiri
8.95B

Foundation for fine-tuning Thai legal NLP tools

Verdict

Going deeper

  • Ecosystem maps — structured-landscape views (memory frameworks, inference runtimes, MCP, coding agents).
  • Execution stacks — recipes that combine models with runtimes + hardware.
  • Frontier index — broader ecosystem-momentum view across coding agents, inference runtimes, memory systems, MCP.
  • Benchmarks — measured tokens-per-second + topology fields across hardware/model/runtime triples.