PrunedHub Qwen3.5 35B A3B 80pct — Hardware Requirements & GPU Compatibility
Chat
PrunedHub Qwen3.5 35B A3B 80pct is a 35B-parameter open language model from GOBA-AI-Labs in the Qwen 3.5 family. At Q4_K_M it needs about 23.10 GB of VRAM — see which GPUs and Macs can run it below.
578 downloads
6 likesSpecifications
- Publisher
- GOBA-AI-Labs
- Family
- Qwen 3.5
- Parameters
- 35B
- Release Date
- 2026-02-25
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does PrunedHub Qwen3.5 35B A3B 80pct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 16.4 GB | — | 14.88 GB | 2-bit quantization with K-quant improvements |
| Q3_K_M | 3.90 | 18.8 GB | — | 17.06 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 23.1 GB | — | 21.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 27.4 GB | — | 24.94 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 31.8 GB | — | 28.88 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 38.5 GB | — | 35.00 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 77 GB | — | 70.00 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run PrunedHub Qwen3.5 35B A3B 80pct?
Q4_K_M · 23.1 GBPrunedHub Qwen3.5 35B A3B 80pct (Q4_K_M) requires 23.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 31+ GB is recommended. 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 PrunedHub Qwen3.5 35B A3B 80pct?
Q4_K_M · 23.1 GB41 devices with unified memory can run PrunedHub Qwen3.5 35B A3B 80pct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does PrunedHub Qwen3.5 35B A3B 80pct need?
PrunedHub Qwen3.5 35B A3B 80pct requires 23.1 GB of VRAM at Q4_K_M, or 77 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 35B × 4.8 bits ÷ 8 = 21 GB
KV Cache + Overhead ≈ 2.1 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M23.1 GB- Can NVIDIA GeForce RTX 4090 run PrunedHub Qwen3.5 35B A3B 80pct?
Yes, at Q4_K_M (23.1 GB) or lower. Higher quantizations like Q5_K_M (27.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for PrunedHub Qwen3.5 35B A3B 80pct?
For PrunedHub Qwen3.5 35B A3B 80pct, Q4_K_M (23.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (27.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 16.4 GB.
VRAM requirement by quantization
Q2_K16.4 GBQ4_K_M ★23.1 GBQ5_K_M27.4 GBQ6_K31.8 GBQ8_038.5 GBBF1677.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run PrunedHub Qwen3.5 35B A3B 80pct on a Mac?
PrunedHub Qwen3.5 35B A3B 80pct requires at least 16.4 GB at Q2_K, 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 PrunedHub Qwen3.5 35B A3B 80pct locally?
Yes — PrunedHub Qwen3.5 35B A3B 80pct can run locally on consumer hardware. At Q4_K_M quantization it needs 23.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is PrunedHub Qwen3.5 35B A3B 80pct?
At Q4_K_M, PrunedHub Qwen3.5 35B A3B 80pct can reach ~191 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~28 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 ÷ 23.1 × 0.65 = ~225 tok/s
Estimated speed at Q4_K_M (23.1 GB)
~225 tok/s~28 tok/s~225 tok/s~191 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of PrunedHub Qwen3.5 35B A3B 80pct?
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 PrunedHub Qwen3.5 35B A3B 80pct?
7 consumer GPUs can run PrunedHub Qwen3.5 35B A3B 80pct at Q4_K_M (23.1 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run PrunedHub Qwen3.5 35B A3B 80pct?
41 devices with unified memory can run PrunedHub Qwen3.5 35B A3B 80pct at Q4_K_M (23.1 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.