Qwen3.6 35B A3B
Qwenhuggingface.co/Qwen/Qwen3.6-35B-A3B
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Updated 52 min ago · first seen 11 Sept 2026
model_01M294WW00HFKTBSY2DM4THGPV
- Parameters
- 36B
- T2 · 55 min ago
- Context
- 262.1K tokens
- T2 · 56 min ago
- Released
- 27 Apr 2026
- T2 · 56 min ago
Specification
- Release date
- 27 Apr 2026
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Parameters
- 36B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Context window
- 262.1K tokens
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Max output
- 235.9K tokens
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Modalities
- image, text, video
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Input modalities
- image, text, video
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Tokenizer
- Qwen
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Hugging Face repo
- Qwen/Qwen3.6-35B-A3B
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Pipeline tag
- image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Downloads
- 3,931,259
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 52 min agomedium
- Likes
- 2,801
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 52 min agomedium
- Last modified
- 2026-04-24T02:53:42+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Openrouter id
- qwen/qwen3.6-35b-a3b
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
22
Source tiers
T222
Freshest observation
52 min ago
Conflicts
None
Modalities
- Modalities
- imagetextvideo
- Input
- imagetextvideo
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 262.1K tokens
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Max output
- 235.9K tokens
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
- Tokenizer
- Qwen
Source:OpenRouter public model & pricing listingT2observed 56 min agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRouterqwen/qwen3.6-35b-a3b | $0.10 | $0.90 | $0.05 | — | 262.1K | 56 min ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 21.2 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 21.2 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 21.2 GB | Yes |
| Apple M2 Ultra | 4bit | — | 21.2 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 21.2 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 21.2 GB | Yes |
| Apple M1 Ultra | 4bit | — | 21.2 GB | Yes |
| Apple M3 Max | 4bit | — | 21.2 GB | Yes |
| Apple M4 Max | 4bit | — | 21.2 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 21.2 GB | Yes |
| Apple M2 Max | 4bit | — | 21.2 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 21.2 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 21.2 GB | Yes |
| Apple M1 Max | 4bit | — | 21.2 GB | Yes |
| Apple M4 Pro | 4bit | — | 21.2 GB | Yes |
| Apple M3 Pro | 4bit | — | 21.2 GB | Yes |
| Apple M1 Pro | 4bit | — | 21.2 GB | Yes |
| Apple M2 Pro | 4bit | — | 21.2 GB | Yes |
| Apple M4 | 4bit | — | 21.2 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 21.2 GB | Yes |
| Apple M2 | 4bit | — | 21.2 GB | Yes |
| Apple M3 | 4bit | — | 21.2 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 21.2 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 21.2 GB | Yes |
| Apple M1 | 4bit | — | 21.2 GB | No |
Ancestors 0
None recorded.
This model
Qwen3.6 35B A3B
36B params
Descendants 0
None recorded.
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Parameters
Parametersparameter_count1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 36B | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
OpenRouter lists Qwen3.6 35B A3B at $0.1 in / $0.9 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8 | model_page | T2· Quality secondary | 10 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/nvidia/Qwen3.6-35B-A3B-NVFP4 | model_page | T2· Quality secondary | 12 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound | model_page | T2· Quality secondary | 26 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/bartowski/Qwen_Qwen3.6-35B-A3B-GGUF | model_page | T2· Quality secondary | 42 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=Qwen&p=0&sort=downloads | listing | T2· Quality secondary | 52 min ago | 2 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 56 min ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.