Qwen3.6 35B A3B REAP 90pct — Hardware Requirements & GPU Compatibility
Chat
Qwen3.6 35B A3B REAP 90pct is a 6.1B-parameter open language model from DJLougen in the Qwen 3.6 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 4.07 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 256K)Best on 24 GB (Q4_K_M · ~163 tok/s · 256K)Macs from 8 GB (Q4_K_M · ~23 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen3.6 35B A3B REAP 90pct
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 run hf.co/DJLougen/Qwen3.6-35B-A3B-REAP-90pct-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 19.8 GB free · 16K context
Download: Qwen3.6-35B-A3B-REAP-90pct-Q4_K_M.gguf3.57 GBDJLougen
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3060 12GB (7 GB headroom) · Q4_K_M
- Generation speed
- ~76 tok/s
- generation speed
- Cost per 1M output tokens
- $0.22
- per 1M output tokens
How Much VRAM Does Qwen3.6 35B A3B REAP 90pct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3 GB | 3.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~196 tok/s | |
| 3.4 GB | 3.6 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~183 tok/s | |
| 4.1 GB | 4.3 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~163 tok/s | |
| 4.8 GB | 5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~147 tok/s | |
| 5.5 GB | 5.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 256K context · ~134 tok/s | |
| 6.5 GB | 6.8 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 256K context · ~118 tok/s | |
| 12.7 GB | 12.9 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 256K context · ~69 tok/s |
Selected Q4_K_M
4-bit medium quantization4.2GBat 16K context
- Weights
- 3.7 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.9 GB free · ~163 tok/s
≥50 tok/s needs ≥222 GB/s · RTX 5090 ~227, RTX 3090 Ti ~163
Which Hardware Can Run Qwen3.6 35B A3B REAP 90pct?
Q4_K_M · 4.1 GBQwen3.6 35B A3B REAP 90pct (Q4_K_M) requires 4.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 6+ GB is recommended. Using the full 262K context window can add up to 2.6 GB, bringing total usage to 6.7 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Qwen3.6 35B A3B REAP 90pct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.9 GB free · up to 256K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~135Simulate output on RTX 3080RTX 2080 Ti~116Simulate output on RTX 2080 TiRTX 3070 Ti~115Simulate output on RTX 3070 TiM3*8 GB~23Simulate output on iMac 24" M3 (8 GB)Orin Nano~24Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~16Simulate output on iPhone 1720 GB
fits · 15.8 GB free · up to 256K ctx
1 GPU
RX 7900 XT~75Simulate output on RX 7900 XT32–40 GB
fits · 27.9 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~227Simulate output on RTX 5090M5 Max36 GB~63Simulate output on Mac Studio M5 Max (36 GB)M532 GB~31Simulate output on MacBook Air 13" M5 (32 GB)Orin~47Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~30Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Qwen3.6 35B A3B REAP 90pct
Qwen 3.6 family · 15 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Yi 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
| Chatglm3 6BZ.ai | — | 5.2 GB | ~159 | same size |
| TLive Omni 4BTaoLiveAIGC | — | 13.3 GB | ~54 | same size |
| Z Image TurboTongyi-MAI | — | 15.9 GB | ~48 | same size |
| Yi 1.5 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
| GPT J 6BEleutherAI | — | 4 GB | ~166 | same size |
Specifications
- Publisher
- DJLougen
- Family
- Qwen 3.6
- Parameters
- 6.1B
- Active parameters
- 3.9B per token
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-06-14
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3.6 35B A3B REAP 90pct need?
Qwen3.6 35B A3B REAP 90pct requires 4.1 GB of VRAM at Q4_K_M, or 12.7 GB at BF16. Full 262K context adds up to 2.6 GB (6.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 6.1B × 4.8 bits ÷ 8 = 3.7 GB
KV Cache + Overhead ≈ 0.4 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 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for Qwen3.6 35B A3B REAP 90pct?
For Qwen3.6 35B A3B REAP 90pct, Q4_K_M (4.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (4.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3.6 35B A3B REAP 90pct on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Qwen3.6 35B A3B REAP 90pct. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run Qwen3.6 35B A3B REAP 90pct locally?
Yes — Qwen3.6 35B A3B REAP 90pct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3.6 35B A3B REAP 90pct?
At Q4_K_M, Qwen3.6 35B A3B REAP 90pct can reach ~117 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~163 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 → 2.6 GB active ÷ (8000 × 0.65) = 0.494 ms, plus 40 layers × 0.055 ms = 2.200 ms, so 1000 ÷ 2.694 ms = ~371 tok/s
Estimated speed at Q4_K_M (4.1 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 REAP 90pct?
At Q4_K_M, the download is about 3.69 GB. The full-precision BF16 version is 12.30 GB. The smallest option (Q2_K) is 2.61 GB.
Which GPUs can run Qwen3.6 35B A3B REAP 90pct?
52 consumer GPUs can run Qwen3.6 35B A3B REAP 90pct at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Qwen3.6 35B A3B REAP 90pct?
163 devices with unified memory can run Qwen3.6 35B A3B REAP 90pct at Q4_K_M (4.1 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.