llmrun
AEON-7Qwen 3.6DFlashDraftModel

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

Chat

AEON DFlash Qwen3.6 35B A3B is a 474M-parameter open language model from AEON-7 in the Qwen 3.6 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 0.60 GB of VRAM — see which GPUs and Macs can run it below.

474M params · dense262K contextMIT80.1K downloads3 likes
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 256KBest on24 GB Q4_K_M · ~1092 tok/s · 256KMacs from8 GB Q4_K_M · ~120 tok/s

MIT

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run AEON DFlash Qwen3.6 35B A3B

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

vLLM
one command · needs vLLM installed
$vllm serve AEON-7/AEON-DFlash-Qwen3.6-35B-A3B --max-model-len 16384

vLLM repo with its own quantisation

Download: Weights on Hugging Face

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
~390 tok/s
generation speed
Cost per 1M output tokens
$0.041
per 1M output tokens

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

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

QuantizationVRAM+32KOn RTX 4090 (reference)
0.5 GB0.8 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 256K context · ~1260 tok/s
0.6 GB0.8 GB3-bit medium — 3-bit medium quantizationFits: 256K context · ~1191 tok/s
0.6 GB0.9 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 256K context · ~1092 tok/s
0.7 GB0.9 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 256K context · ~1008 tok/s
0.7 GB1 GB6-bit, very good — 6-bit quantization, very good qualityFits: 256K context · ~923 tok/s
0.8 GB1 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 256K context · ~829 tok/s
1.3 GB1.5 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 256K context · ~520 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

0.7GBat 16K context

Weights
0.3 GB
KV cache
0.1 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 23.3 GB free · ~1092 tok/s

≥50 tok/s needs ≥46 GB/s · RTX 5090 ~1941, M5 Ultra ~1433

Which Hardware Can Run AEON DFlash Qwen3.6 35B A3B?

Q4_K_M · 0.6 GB

AEON DFlash Qwen3.6 35B A3B (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 2.1 GB, bringing total usage to 2.7 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run AEON DFlash Qwen3.6 35B A3B, 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 · 0.7 GB · ~295 tok/s · 256K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 0.7 GB · ~390 tok/s · 256K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 0.7 GB · ~485 tok/s · 256K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 0.7 GB · ~1092 tok/s · 256K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 0.7 GB · ~140 tok/s · 256KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 0.7 GB · ~637 tok/s · 256KMacs →

Alternatives to AEON DFlash Qwen3.6 35B A3B

Qwen 3.6 family · 18 models →

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
LFM2.5 VL 450MLiquid AI—0.8 GB~1024same size
SmolVLM2 500M Video InstructHugging Face—0.9 GB~950same size
SmolVLM 500M InstructHugging Face—0.9 GB~950same size
TIPO 500M FtKBlueLeaf—0.8 GB~809same size
Qwen2.5 0.5B InstructAlibaba—0.8 GB~1057same size
Qwen2 0.5B InstructAlibaba—0.8 GB~1057same size

Specifications

Publisher
AEON-7
Family
Qwen 3.6
Parameters
474M
Architecture
DFlashDraftModel
Context Length
262,144 tokens
Vocabulary Size
248,320
Release Date
2026-06-28
License
MIT

Frequently Asked Questions

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

AEON DFlash Qwen3.6 35B A3B requires 0.6 GB of VRAM at Q4_K_M, or 1.3 GB at BF16. Full 262K context adds up to 2.1 GB (2.7 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 474M × 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 ≈ 2.4 GB (at full 262K context)

VRAM usage by quantization

0.6 GB
2.7 GB

Learn more about VRAM estimation →

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

For AEON DFlash Qwen3.6 35B A3B, 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 0.5 GB.

VRAM requirement by quantization

Q2_K
0.5 GB
Q4_K_M ★
0.6 GB
Q5_K_M
0.7 GB
Q6_K
0.7 GB
Q8_0
0.8 GB
BF16
1.3 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

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

Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run AEON DFlash Qwen3.6 35B A3B. 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 AEON DFlash Qwen3.6 35B A3B locally?

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

How fast is AEON DFlash Qwen3.6 35B A3B?

At Q4_K_M, AEON DFlash Qwen3.6 35B A3B can reach ~8000 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1092 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 ÷ 0.6 × 0.65 = ~8667 tok/s

Estimated speed at Q4_K_M (0.6 GB)

~8667 tok/s
~1092 tok/s
~8667 tok/s
~8000 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 AEON DFlash Qwen3.6 35B A3B?

At Q4_K_M, the download is about 0.28 GB. The full-precision BF16 version is 0.95 GB. The smallest option (Q2_K) is 0.20 GB.

Which GPUs can run AEON DFlash Qwen3.6 35B A3B?

114 consumer GPUs can run AEON DFlash Qwen3.6 35B A3B 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 AEON DFlash Qwen3.6 35B A3B?

185 devices with unified memory can run AEON DFlash Qwen3.6 35B A3B 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.