Qwen3.6 35B A3B DFlash — Hardware Requirements & GPU Compatibility
Chat
Qwen3.6 35B A3B DFlash is a 35B-parameter open language model from z-lab in the Qwen 3.6 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 21.33 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 16 GB (Q2_K · 64K)Best on 24 GB (Q4_K_M · ~321 tok/s · 128K)Macs from 24 GB (Q3_K_M · ~123 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen3.6 35B A3B DFlash
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/Anbeeld/Qwen3.6-35B-A3B-DFlash-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 2.5 GB free · 16K context
Download: qwen36-35b-a3b-dflash-Q4_K_M.gguf0.24 GBAnbeeld
Other ways
each opens step-by-stepRun in cloud
Fits on RTX PRO 4500 (32 GB) (10 GB headroom) · Q4_K_M
- Generation speed
- ~288 tok/s
- generation speed
- Cost per 1M output tokens
- $0.33
- per 1M output tokens
How Much VRAM Does Qwen3.6 35B A3B DFlash Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 15.2 GB | 15.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~431 tok/s | |
| 17.4 GB | 17.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~384 tok/s | |
| 21.3 GB | 21.7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~321 tok/s | |
| 25.3 GB | 25.6 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 25.4 GB | |
| 29.2 GB | 29.6 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 29.4 GB | |
| 35.3 GB | 35.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 35.5 GB | |
| 70.3 GB | 70.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 70.5 GB |
Selected Q4_K_M
4-bit medium quantization21.5GBat 16K context
- Weights
- 21.0 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 2.5 GB free · ~321 tok/s
≥50 tok/s needs ≥143 GB/s · RTX 5090 ~526, RTX 3090 Ti ~321
Which Hardware Can Run Qwen3.6 35B A3B DFlash?
Q4_K_M · 21.3 GBQwen3.6 35B A3B DFlash (Q4_K_M) requires 21.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 28+ GB is recommended. Using the full 262K context window can add up to 3.2 GB, bringing total usage to 24.5 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 100 devices with unified memory can run Qwen3.6 35B A3B DFlash, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit Q3_K_M (17.6 GB)
1 GPU
RX 7900 XT~232Simulate output on RX 7900 XT32–40 GB
fits · 10.5 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~526Simulate output on RTX 5090M5 Max36 GB~145Simulate output on Mac Studio M5 Max (36 GB)M532 GB~55Simulate output on MacBook Air 13" M5 (32 GB)Orin~71Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~47Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Qwen3.6 35B A3B DFlash
Qwen 3.6 family · 15 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.7 35B A3BOpenBMB | — | 22.1 GB | ~169 | same size |
| Llm Jp 4.1 33B Thinkingllm-jp | — | 22.5 GB | ~35 | same size |
| Agnes 3.0 FlashAgnes-AI | — | 22.1 GB | ~35 | same size |
| Ornith 1.5 35B A3Bornith-ai | — | 22 GB | ~151 | same size |
| Agents A1InternScience | — | 21.5 GB | ~171 | same size |
| Intern S2 PreviewInternLM | — | 73.2 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- z-lab
- Family
- Qwen 3.6
- Parameters
- 35B
- Active parameters
- 3B per token
- Architecture
- DFlashDraftModel
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-04-17
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3.6 35B A3B DFlash need?
Qwen3.6 35B A3B DFlash requires 21.3 GB of VRAM at Q4_K_M, or 70.3 GB at BF16. Full 262K context adds up to 3.2 GB (24.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 35B × 4.8 bits ÷ 8 = 21 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 3.5 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Qwen3.6 35B A3B DFlash?
Yes, at Q4_K_M (21.3 GB) or lower. Higher quantizations like Q5_K_M (25.3 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Qwen3.6 35B A3B DFlash?
For Qwen3.6 35B A3B DFlash, Q4_K_M (21.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (25.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 15.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3.6 35B A3B DFlash on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Qwen3.6 35B A3B DFlash, the smallest at Q3_K_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 21.3 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).
Can I run Qwen3.6 35B A3B DFlash locally?
Yes — Qwen3.6 35B A3B DFlash can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3.6 35B A3B DFlash?
At Q4_K_M, Qwen3.6 35B A3B DFlash can reach ~633 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~321 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 1.8 GB active ÷ (8000 × 0.65) = 0.3516 ms, plus 6 layers × 0.055 ms = 0.3300 ms, so 1000 ÷ 0.6816 ms = ~1467 tok/s
Estimated speed at Q4_K_M (21.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen3.6 35B A3B DFlash?
At Q4_K_M, the download is about 21.00 GB. The full-precision BF16 version is 70.00 GB. The smallest option (Q2_K) is 14.88 GB.
Which GPUs can run Qwen3.6 35B A3B DFlash?
7 consumer GPUs can run Qwen3.6 35B A3B DFlash at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Qwen3.6 35B A3B DFlash?
100 devices with unified memory can run Qwen3.6 35B A3B DFlash at Q4_K_M (21.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.