llmrun
incoaiQwen 3.6DFlash2DraftModel

Qwen3.6 35B A3B DFlash2 — Hardware Requirements & GPU Compatibility

Chat

Qwen3.6 35B A3B DFlash2 is a 526M-parameter open language model from incoai in the Qwen 3.6 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 0.64 GB of VRAM — see which GPUs and Macs can run it below.

526M params · dense262K contextApache 2.099.2K downloads24 likes6.2K quant downloads
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 256KBest on24 GB Q4_K_M · ~1024 tok/s · 256KMacs from8 GB Q4_K_M · ~112 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Qwen3.6 35B A3B DFlash2

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

Ollama
one command · needs Ollama installed
$ollama run hf.co/aminya/Qwen3.6-35B-A3B-DFlash2-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 23.2 GB free · 16K context

Download: Qwen3.6-35B-A3B-DFlash2-Q4_K_M.gguf0.31 GBaminya

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 3060 12GB (11 GB headroom) · Q4_K_M

Generation speed
~366 tok/s
generation speed
Cost per 1M output tokens
$0.044
per 1M output tokens

How Much VRAM Does Qwen3.6 35B A3B DFlash2 Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
0.6 GB0.9 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 256K context · ~1191 tok/s
0.6 GB0.9 GB3-bit · i-quant small — Importance-weighted 3-bit, smallFits: 256K context · ~1191 tok/s
0.6 GB0.9 GB3-bit · i-quant medium — Importance-weighted 3-bit, mediumFits: 256K context · ~1170 tok/s
0.6 GB1 GB3-bit medium — 3-bit medium quantizationFits: 256K context · ~1130 tok/s
0.6 GB1 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 256K context · ~1024 tok/s
0.7 GB1.1 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 256K context · ~936 tok/s
0.8 GB1.1 GB6-bit, very good — 6-bit quantization, very good qualityFits: 256K context · ~862 tok/s
0.8 GB1.2 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 256K context · ~771 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

0.8GBat 16K context

Weights
0.3 GB
KV cache
0.2 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 23.2 GB free · ~1024 tok/s

≥50 tok/s needs ≥49 GB/s · RTX 5090 ~1820, M5 Ultra ~1343

Which Hardware Can Run Qwen3.6 35B A3B DFlash2?

Q4_K_M · 0.6 GB

Qwen3.6 35B A3B DFlash2 (Q4_K_M) requires 0.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 262K context window can add up to 3.2 GB, bringing total usage to 3.8 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run Qwen3.6 35B A3B DFlash2, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 0.8 GB · ~276 tok/s · 256K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 0.8 GB · ~366 tok/s · 256K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 0.8 GB · ~455 tok/s · 256K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 0.8 GB · ~1024 tok/s · 256K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 0.8 GB · ~131 tok/s · 256KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 0.8 GB · ~597 tok/s · 256KMacs →

Alternatives to Qwen3.6 35B A3B DFlash2

Qwen 3.6 family · 18 models →

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
SmolVLM2 500M Video InstructHugging Face—0.9 GB~950same size
SmolVLM 500M InstructHugging Face—0.9 GB~950same size
Falcon H1 0.5B BaseTII UAE—1.2 GB~950same size
TIPO 500M FtKBlueLeaf—0.8 GB~809same size
Qwen2.5 0.5B InstructAlibaba—0.8 GB~1057same size
H2o Danube3 500M Chath2oai—1 GB~923same size

Specifications

Publisher
incoai
Family
Qwen 3.6
Parameters
526M
Architecture
DFlash2DraftModel
Context Length
262,144 tokens
Vocabulary Size
248,320
Release Date
2026-09-17
License
Apache 2.0

Frequently Asked Questions

How much VRAM does Qwen3.6 35B A3B DFlash2 need?

Qwen3.6 35B A3B DFlash2 requires 0.6 GB of VRAM at Q4_K_M, or 1.4 GB at BF16. Full 262K context adds up to 3.2 GB (3.8 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 526M × 4.8 bits ÷ 8 = 0.3 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

0.6 GB
3.8 GB

Learn more about VRAM estimation →

What's the best quantization for Qwen3.6 35B A3B DFlash2?

For Qwen3.6 35B A3B DFlash2, Q4_K_M (0.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.6 GB.

VRAM requirement by quantization

Q2_K
0.6 GB
Q3_K_M
0.6 GB
IQ4_NL
0.6 GB
Q4_K_M ★
0.6 GB
Q6_K
0.8 GB
BF16
1.4 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Qwen3.6 35B A3B DFlash2 on a Mac?

Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run Qwen3.6 35B A3B DFlash2. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.6 GB of usable unified memory (RAM minus macOS overhead).

Can I run Qwen3.6 35B A3B DFlash2 locally?

Yes — Qwen3.6 35B A3B DFlash2 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Qwen3.6 35B A3B DFlash2?

At Q4_K_M, Qwen3.6 35B A3B DFlash2 can reach ~7500 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1024 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 0.64 × 0.65 = ~8125 tok/s

Estimated speed at Q4_K_M (0.6 GB)

~8125 tok/s
~1024 tok/s
~8125 tok/s
~7500 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Qwen3.6 35B A3B DFlash2?

At Q4_K_M, the download is about 0.32 GB. The full-precision BF16 version is 1.05 GB. The smallest option (Q2_K) is 0.22 GB.

Which GPUs can run Qwen3.6 35B A3B DFlash2?

114 consumer GPUs can run Qwen3.6 35B A3B DFlash2 at Q4_K_M. Top options include AMD Radeon RX 5600 XT, AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB. 114 GPUs have plenty of headroom for comfortable inference.

Which devices can run Qwen3.6 35B A3B DFlash2?

185 devices with unified memory can run Qwen3.6 35B A3B DFlash2 at Q4_K_M (0.6 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.