Qwythos 9B v2 Heretic — Hardware Requirements & GPU Compatibility
ChatReasoning
Qwythos 9B v2 Heretic is a 9.4B-parameter open language model from WaveCut. It supports a context window of up to 1,048,576 tokens. At Q4_K_M it needs about 6.21 GB of VRAM — see which GPUs and Macs can run it below.
396 downloads
1 likesSpecifications
- Publisher
- WaveCut
- Parameters
- 9.4B
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-07-13
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Qwythos 9B v2 Heretic Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 4.6 GB | 141.7 GB | 4.00 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 5.2 GB | 142.3 GB | 4.59 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 6.2 GB | 143.4 GB | 5.65 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 7.3 GB | 144.4 GB | 6.70 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 8.3 GB | 145.5 GB | 7.76 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 10.0 GB | 147.2 GB | 9.41 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 19.4 GB | 156.6 GB | 18.82 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 Qwythos 9B v2 Heretic?
Q4_K_M · 6.2 GBQwythos 9B v2 Heretic (Q4_K_M) requires 6.2 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 143.4 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 Heretic?
Q4_K_M · 6.2 GB58 devices with unified memory can run Qwythos 9B v2 Heretic, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomWhere to Download Qwythos 9B v2 Heretic
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 Heretic need?
Qwythos 9B v2 Heretic requires 6.2 GB of VRAM at Q4_K_M, or 19.4 GB at BF16. Full 1049K context adds up to 137.2 GB (143.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 9.4B × 4.8 bits ÷ 8 = 5.6 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 137.8 GB (at full 1049K context)
VRAM usage by quantization
Q4_K_M6.2 GBQ4_K_M + full context143.4 GB- What's the best quantization for Qwythos 9B v2 Heretic?
For Qwythos 9B v2 Heretic, Q4_K_M (6.2 GB) offers the best balance of quality and VRAM usage. Q5_K_M (7.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 4.6 GB.
VRAM requirement by quantization
Q2_K4.6 GBQ4_K_M ★6.2 GBQ5_K_M7.3 GBQ6_K8.3 GBQ8_010.0 GBBF1619.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwythos 9B v2 Heretic on a Mac?
Qwythos 9B v2 Heretic requires at least 4.6 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 Qwythos 9B v2 Heretic locally?
Yes — Qwythos 9B v2 Heretic can run locally on consumer hardware. At Q4_K_M quantization it needs 6.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwythos 9B v2 Heretic?
At Q4_K_M, Qwythos 9B v2 Heretic can reach ~709 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~106 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 ÷ 6.2 × 0.65 = ~837 tok/s
Estimated speed at Q4_K_M (6.2 GB)
~837 tok/s~106 tok/s~837 tok/s~709 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 Heretic?
At Q4_K_M, the download is about 5.65 GB. The full-precision BF16 version is 18.82 GB. The smallest option (Q2_K) is 4.00 GB.
- Which GPUs can run Qwythos 9B v2 Heretic?
50 consumer GPUs can run Qwythos 9B v2 Heretic at Q4_K_M (6.2 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 Heretic?
59 devices with unified memory can run Qwythos 9B v2 Heretic at Q4_K_M (6.2 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.