Alibaba

Qwen 3.6 35B A3B

Name: Qwen 3.6 35B A3B
Rating: 94 (64 reviews)
Author: Alibaba

Frontier

HuggingFace

5.7MDownloads2.0KLikesApr 2026Veröffentlicht262K TokenKontextApache 2.0Lizenz98 HerausragendQualität

Qwen 3.6 35B A3B (35B parameters) requires approximately 28.5 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 3B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 33 GB of VRAM.

Loslegen

— kopieren & einfügen, um lokal auszuführen

Copy-paste commands to run Qwen 3.6 35B A3B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "Qwen/Qwen3.6-35B-A3B" \
  --hf-file "Qwen3.6-35B-A3B-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Quick specs

Parameters35B (3B active)

Architecturemoe (MoE)

Context262K tokens

Modalitytext+vision

Min RAM13.7 GB

Rec. RAM21.3 GB (Q4_K_M)

LicenseApache 2.0

FamilyQwen

✓ Vision✓ Code✓ Chat✓ Reasoning

About this model

Qwen 3.6 35B A3B is the first open-weight Qwen 3.6 model, a multimodal MoE release focused on stronger agentic coding, long-context reasoning, and more stable repository-scale workflows.

•35B total params with only 3B active per token
•262K native context with preserve-thinking support
•Multimodal open-weights model tuned for coding and agent workflows

Verwandte Modelle

Schnellauswahl

Bestes BudgetS

Mac mini M4 64GB~$1,099 — 11 tok/s

Beste GesamtwahlS

NVIDIA A100 40GB~$10,000 — 126 tok/s

Beste Hardware

Top-Empfehlungen für Qwen 3.6 35B A3B

RTX PRO 5000 Blackwell 48GBS

Dieses Modell ausführen

Qwen 3.6 35B A3B on NVIDIA A100 40GB Qwen 3.6 35B A3B on RTX 6000 Ada 48GB Qwen 3.6 35B A3B on RTX PRO 5000 Blackwell 48GB

Quantisierungsoptionen

VRAM-Schätzungen nach Quantisierungsstufe

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	—
Q3_K_S	3	17.2 GB	Low	—
NVFP4	4	19.6 GB	Medium	—
Q4_K_M	4	21.3 GB	Medium	—
Q5_K_M	5	25.2 GB	High	—
Q6_K	6	28.7 GB	High	—
Q8_0	8	37.5 GB	Very High	—
F16	16	71.8 GB	Maximum	—

Quality benchmarks

Qwen 3.6 35B A3B benchmark scores

Benchmark verified

Coding

SWE-bench Verified73.4%

HumanEval+—

Aider Polyglot—

LiveCodeBench80.4%

Reasoning

MMLU-Pro85.2%

GPQA Diamond86.0%

MATH-500—

ARC Challenge—

Source: official · 2026-04-15

Hardware-Kompatibilität

Eignungsschätzungen für alle Hardware

Rechner öffnen

Computing compatibility...

Speicheraufschlüsselung

Reference: RTX 2060 6GB

Weights21.3 GB

KV Cache4.1 GB

Runtime2.4 GB

Headroom0.6 GB

Häufig gestellte Fragen

FAQ — Qwen 3.6 35B A3B

Siehe auch

Quantisierungsleitfaden Bewertungsmethodik Rechner öffnen