Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated — Hardware Requirements & GPU Compatibility
Vision
Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated is a 122.6B-parameter open language model from OpenYourMind in the Kimi K2 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 73.91 GB of VRAM — see which GPUs and Macs can run it below.
182 downloads
17 likesSpecifications
- Publisher
- OpenYourMind
- Family
- Kimi K2
- Parameters
- 122.6B
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-05-20
- License
- MIT
Get Started
How Much VRAM Does Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 52.5 GB | 62.0 GB | 52.09 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 54 GB | 63.6 GB | 53.62 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 60.1 GB | 69.7 GB | 59.75 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 73.9 GB | 83.5 GB | 73.54 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 87.7 GB | 97.3 GB | 87.33 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 101.5 GB | 111.1 GB | 101.11 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 122.9 GB | 132.5 GB | 122.56 GB | 8-bit quantization, near-lossless |
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 Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated?
Q4_K_M · 73.9 GBQwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated (Q4_K_M) requires 73.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 97+ GB is recommended. Using the full 262K context window can add up to 9.6 GB, bringing total usage to 83.5 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated?
Q4_K_M · 73.9 GB18 devices with unified memory can run Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated
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 Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated need?
Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated requires 73.9 GB of VRAM at Q4_K_M, or 245.5 GB at BF16. Full 262K context adds up to 9.6 GB (83.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 122.6B × 4.8 bits ÷ 8 = 73.5 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 10 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M73.9 GBQ4_K_M + full context83.5 GB- Can NVIDIA GeForce RTX 5090 run Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated?
No — Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated requires at least 52.5 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated?
For Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated, Q4_K_M (73.9 GB) offers the best balance of quality and VRAM usage. Q5_K_S (84.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 52.5 GB.
VRAM requirement by quantization
Q2_K52.5 GBQ3_K_L63.2 GBQ4_K_M ★73.9 GBQ5_K_S84.6 GBQ5_K_M87.7 GBBF16245.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated on a Mac?
Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated requires at least 52.5 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 Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated locally?
Yes — Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated can run locally on consumer hardware. At Q4_K_M quantization it needs 73.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated?
At Q4_K_M, Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated can reach ~92 tok/s on AMD Instinct MI350X. 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 ÷ 73.9 × 0.65 = ~261 tok/s
Estimated speed at Q4_K_M (73.9 GB)
~261 tok/s~261 tok/s~219 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated?
At Q4_K_M, the download is about 73.54 GB. The full-precision BF16 version is 245.13 GB. The smallest option (Q2_K) is 52.09 GB.
- Which GPUs can run Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated?
No single consumer GPU has enough VRAM to run Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated at Q4_K_M (73.9 GB). Multi-GPU or professional hardware is required.
- Which devices can run Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated?
19 devices with unified memory can run Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated at Q4_K_M (73.9 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), 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.