Qwen3.8 35B A3B Distill — Hardware Requirements & GPU Compatibility
ChatVisionReasoningFunctions
Qwen3.8 35B A3B Distill is a 35.1B-parameter open language model from empero-ai in the Qwen 3.8 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 21.45 GB of VRAM — see which GPUs and Macs can run it below.
4.6K downloads
58 likesSpecifications
- Publisher
- empero-ai
- Family
- Qwen 3.8
- Parameters
- 35.1B
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-09-16
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Qwen3.8 35B A3B Distill Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| IQ2_M | 2.70 | 12.2 GB | 22.9 GB | 11.85 GB | Importance-weighted 2-bit, medium |
| Q2_K | 3.40 | 15.3 GB | 26.0 GB | 14.92 GB | 2-bit quantization with K-quant improvements |
| IQ3_M | 3.60 | 16.2 GB | 26.8 GB | 15.80 GB | Importance-weighted 3-bit, medium |
| Q3_K_M | 3.90 | 17.5 GB | 28.1 GB | 17.11 GB | 3-bit medium quantization |
| IQ4_XS | 4.30 | 19.3 GB | 29.9 GB | 18.87 GB | Importance-weighted 4-bit, compact |
| Q4_K_M | 4.80 | 21.4 GB | 32.1 GB | 21.06 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 25.4 GB | 36.0 GB | 25.01 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 29.4 GB | 40 GB | 28.96 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 35.5 GB | 46.1 GB | 35.11 GB | 8-bit quantization, near-lossless |
| BF16 | 16.00 | 70.6 GB | 81.3 GB | 70.21 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Qwen3.8 35B A3B Distill?
Q4_K_M · 21.4 GBQwen3.8 35B A3B Distill (Q4_K_M) requires 21.4 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 10.7 GB, bringing total usage to 32.1 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Which Devices Can Run Qwen3.8 35B A3B Distill?
Q4_K_M · 21.4 GB41 devices with unified memory can run Qwen3.8 35B A3B Distill, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, NVIDIA Jetson AGX Orin 32GB.
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Qwen3.8 35B A3B Distill
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Qwen3.8 35B A3B Distill need?
Qwen3.8 35B A3B Distill requires 21.4 GB of VRAM at Q4_K_M, or 70.6 GB at BF16. Full 262K context adds up to 10.7 GB (32.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 35.1B × 4.8 bits ÷ 8 = 21.1 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 11 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M21.4 GBQ4_K_M + full context32.1 GB- Can NVIDIA GeForce RTX 4090 run Qwen3.8 35B A3B Distill?
Yes, at Q4_K_M (21.4 GB) or lower. Higher quantizations like Q5_K_M (25.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Qwen3.8 35B A3B Distill?
For Qwen3.8 35B A3B Distill, Q4_K_M (21.4 GB) offers the best balance of quality and VRAM usage. Q5_K_M (25.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_M at 12.2 GB.
VRAM requirement by quantization
IQ2_M12.2 GBIQ3_M16.2 GBQ4_K_M ★21.4 GBQ5_K_M25.4 GBQ6_K29.4 GBBF1670.6 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwen3.8 35B A3B Distill on a Mac?
Qwen3.8 35B A3B Distill requires at least 12.2 GB at IQ2_M, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Qwen3.8 35B A3B Distill locally?
Yes — Qwen3.8 35B A3B Distill can run locally on consumer hardware. At Q4_K_M quantization it needs 21.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen3.8 35B A3B Distill?
At Q4_K_M, Qwen3.8 35B A3B Distill can reach ~118 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~171 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 ÷ 21.4 × 0.65 = ~376 tok/s
Estimated speed at Q4_K_M (21.4 GB)
~376 tok/s~171 tok/s~376 tok/s~339 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwen3.8 35B A3B Distill?
At Q4_K_M, the download is about 21.06 GB. The full-precision BF16 version is 70.21 GB. The smallest option (IQ2_M) is 11.85 GB.
- Which GPUs can run Qwen3.8 35B A3B Distill?
7 consumer GPUs can run Qwen3.8 35B A3B Distill at Q4_K_M (21.4 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run Qwen3.8 35B A3B Distill?
41 devices with unified memory can run Qwen3.8 35B A3B Distill at Q4_K_M (21.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.