Qwythos 9B v2 — Hardware Requirements & GPU Compatibility
ChatReasoning
Qwythos 9B v2 is a 9.7B-parameter open language model from empero-ai. It supports a context window of up to 1,048,576 tokens. At Q4_K_M it needs about 6.36 GB of VRAM — see which GPUs and Macs can run it below.
9.5K downloads
142 likesSpecifications
- Publisher
- empero-ai
- Parameters
- 9.7B
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-07-09
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Qwythos 9B v2 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 4.7 GB | 141.8 GB | 4.10 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 4.8 GB | 142.0 GB | 4.22 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 5.3 GB | 142.4 GB | 4.71 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 5.4 GB | 142.6 GB | 4.83 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 6.4 GB | 143.5 GB | 5.79 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 7.5 GB | 144.6 GB | 6.88 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 8.5 GB | 145.7 GB | 7.96 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 10.2 GB | 147.4 GB | 9.65 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Qwythos 9B v2?
Q4_K_M · 6.4 GBQwythos 9B v2 (Q4_K_M) requires 6.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 9+ GB is recommended. Using the full 1049K context window can add up to 137.2 GB, bringing total usage to 143.5 GB. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Qwythos 9B v2?
Q4_K_M · 6.4 GB58 devices with unified memory can run Qwythos 9B v2, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomWhere to Download Qwythos 9B v2
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 Qwythos 9B v2 need?
Qwythos 9B v2 requires 6.4 GB of VRAM at Q4_K_M, or 19.9 GB at BF16. Full 1049K context adds up to 137.2 GB (143.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 9.7B × 4.8 bits ÷ 8 = 5.8 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 137.7 GB (at full 1049K context)
VRAM usage by quantization
Q4_K_M6.4 GBQ4_K_M + full context143.5 GB- What's the best quantization for Qwythos 9B v2?
For Qwythos 9B v2, Q4_K_M (6.4 GB) offers the best balance of quality and VRAM usage. Q4_K_L (6.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_M at 3.8 GB.
VRAM requirement by quantization
IQ2_M3.8 GBIQ3_M4.9 GBIQ4_NL6.0 GBQ4_K_M ★6.4 GBQ5_K_S7.2 GBBF1619.9 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwythos 9B v2 on a Mac?
Qwythos 9B v2 requires at least 3.8 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 Qwythos 9B v2 locally?
Yes — Qwythos 9B v2 can run locally on consumer hardware. At Q4_K_M quantization it needs 6.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwythos 9B v2?
At Q4_K_M, Qwythos 9B v2 can reach ~692 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~103 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 ÷ 6.4 × 0.65 = ~818 tok/s
Estimated speed at Q4_K_M (6.4 GB)
~818 tok/s~103 tok/s~818 tok/s~692 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwythos 9B v2?
At Q4_K_M, the download is about 5.79 GB. The full-precision BF16 version is 19.31 GB. The smallest option (IQ2_M) is 3.26 GB.
- Which GPUs can run Qwythos 9B v2?
50 consumer GPUs can run Qwythos 9B v2 at Q4_K_M (6.4 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 39 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Qwythos 9B v2?
59 devices with unified memory can run Qwythos 9B v2 at Q4_K_M (6.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.