KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS — Hardware Requirements & GPU Compatibility
ChatCodeFunctions
KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS is a 34.7B-parameter open language model from KridgeDookie in the Phi family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 21.18 GB of VRAM — see which GPUs and Macs can run it below.
19.9K downloads
4 likesSpecifications
- Publisher
- KridgeDookie
- Family
- Phi
- Parameters
- 34.7B
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-08-07
- License
- Apache 2.0
Get Started
How Much VRAM Does KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 15.1 GB | 25.8 GB | 14.73 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 17.3 GB | 27.9 GB | 16.90 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 21.2 GB | 31.8 GB | 20.80 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 25.1 GB | 35.7 GB | 24.70 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 29.0 GB | 39.6 GB | 28.60 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 35.0 GB | 45.7 GB | 34.66 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 69.7 GB | 80.4 GB | 69.32 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 KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS?
Q4_K_M · 21.2 GBKAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS (Q4_K_M) requires 21.2 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 10.6 GB, bringing total usage to 31.8 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS?
Q4_K_M · 21.2 GB41 devices with unified memory can run KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS, 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 KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS need?
KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS requires 21.2 GB of VRAM at Q4_K_M, or 69.7 GB at BF16. Full 262K context adds up to 10.6 GB (31.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 34.7B × 4.8 bits ÷ 8 = 20.8 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 11 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M21.2 GBQ4_K_M + full context31.8 GB- Can NVIDIA GeForce RTX 4090 run KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS?
Yes, at Q4_K_M (21.2 GB) or lower. Higher quantizations like Q5_K_M (25.1 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS?
For KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS, Q4_K_M (21.2 GB) offers the best balance of quality and VRAM usage. Q5_K_M (25.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 15.1 GB.
VRAM requirement by quantization
Q2_K15.1 GBQ4_K_M ★21.2 GBQ5_K_M25.1 GBQ6_K29.0 GBQ8_035.0 GBBF1669.7 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS on a Mac?
KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS requires at least 15.1 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 KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS locally?
Yes — KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS can run locally on consumer hardware. At Q4_K_M quantization it needs 21.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS?
At Q4_K_M, KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS can reach ~227 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~31 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 ÷ 21.2 × 0.65 = ~246 tok/s
Estimated speed at Q4_K_M (21.2 GB)
~246 tok/s~31 tok/s~246 tok/s~227 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS?
At Q4_K_M, the download is about 20.80 GB. The full-precision BF16 version is 69.32 GB. The smallest option (Q2_K) is 14.73 GB.
- Which GPUs can run KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS?
7 consumer GPUs can run KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS at Q4_K_M (21.2 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS?
41 devices with unified memory can run KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS at Q4_K_M (21.2 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.