KAT Coder V2.5 Dev NVFP4A16 — Hardware Requirements & GPU Compatibility
ChatCodeFunctionsKAT Coder V2.5 Dev NVFP4A16 is a 20.4B-parameter open language model from sahilchachra. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 12.62 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 12 GB (Q3_K_M · 128K)Best on 24 GB (Q4_K_M · ~52 tok/s · 256K)Macs from 16 GB (Q3_K_M · ~14 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run KAT Coder V2.5 Dev NVFP4A16
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve sahilchachra/KAT-Coder-V2.5-Dev-NVFP4A16 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3090 Ti (24 GB) (11 GB headroom) · Q4_K_M
- Generation speed
- ~52 tok/s
- generation speed
- Cost per 1M output tokens
- $1.30
- per 1M output tokens
How Much VRAM Does KAT Coder V2.5 Dev NVFP4A16 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 9.1 GB | 9.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~72 tok/s | |
| 10.3 GB | 10.6 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~63 tok/s | |
| 12.6 GB | 12.9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~52 tok/s | |
| 14.9 GB | 15.2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~44 tok/s | |
| 17.2 GB | 17.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 256K context · ~38 tok/s | |
| 20.8 GB | 21 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 256K context · ~32 tok/s | |
| 41.2 GB | 41.4 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 41.3 GB |
Selected Q4_K_M
4-bit medium quantization12.7GBat 16K context
- Weights
- 12.2 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Which Hardware Can Run KAT Coder V2.5 Dev NVFP4A16?
Q4_K_M · 12.6 GBKAT Coder V2.5 Dev NVFP4A16 (Q4_K_M) requires 12.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 17+ GB is recommended. Using the full 262K context window can add up to 2.6 GB, bringing total usage to 15.2 GB. 30 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 140 devices with unified memory can run KAT Coder V2.5 Dev NVFP4A16, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), MacBook Pro 14" M3 Pro (18 GB).
16–18 GB
16–18 GB tier →fits · 3.3 GB free · up to 256K ctx
22 GPUs · 1 Mac class · 1 device family
RTX 5080~49Simulate output on RTX 5080RTX 5070 Ti~46Simulate output on RTX 5070 TiRTX 5080 Laptop GPU~46Simulate output on RTX 5080 Laptop GPUM3 Pro*18 GB~8Simulate output on MacBook Pro 14" M3 Pro (18 GB)Orin NX~5Simulate output on NVIDIA Jetson Orin NX 16GB20 GB
fits · 7.3 GB free · up to 256K ctx
1 GPU
RX 7900 XT~38Simulate output on RX 7900 XT32–40 GB
fits · 19.3 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~92Simulate output on RTX 5090M5 Max*36 GB~26Simulate output on Mac Studio M5 Max (36 GB)M632 GB~9Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~16Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~11Simulate output on NVIDIA Jetson AGX Orin 32GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
3| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| InternVL3 5 GPT OSS 20B A4B Preview HFOpenGVLab | — | 13.6 GB | ~180 | same size |
| Internlm 20BInternLM | — | 45.3 GB | —needs > 24 GB | same size |
| ERNIE 4.5 21B A3B ThinkingBaidu | — | 14.3 GB | ~213 | same size |
Specifications
- Publisher
- sahilchachra
- Parameters
- 20.4B
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-07-24
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does KAT Coder V2.5 Dev NVFP4A16 need?
KAT Coder V2.5 Dev NVFP4A16 requires 12.6 GB of VRAM at Q4_K_M, or 41.2 GB at BF16. Full 262K context adds up to 2.6 GB (15.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 20.4B × 4.8 bits ÷ 8 = 12.2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 3 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run KAT Coder V2.5 Dev NVFP4A16?
Yes, at Q8_0 (20.8 GB) or lower. Higher quantizations like BF16 (41.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for KAT Coder V2.5 Dev NVFP4A16?
For KAT Coder V2.5 Dev NVFP4A16, Q4_K_M (12.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (14.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 9.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run KAT Coder V2.5 Dev NVFP4A16 on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 145 other Macs can run KAT Coder V2.5 Dev NVFP4A16, the smallest at Q3_K_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 12.6 GB of usable unified memory (RAM minus macOS overhead), from MacBook Pro 14" M3 Pro (18 GB).
Can I run KAT Coder V2.5 Dev NVFP4A16 locally?
Yes — KAT Coder V2.5 Dev NVFP4A16 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is KAT Coder V2.5 Dev NVFP4A16?
At Q4_K_M, KAT Coder V2.5 Dev NVFP4A16 can reach ~380 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~52 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 ÷ 12.62 × 0.65 = ~412 tok/s
Estimated speed at Q4_K_M (12.6 GB)
Real-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 NVFP4A16?
At Q4_K_M, the download is about 12.24 GB. The full-precision BF16 version is 40.79 GB. The smallest option (Q2_K) is 8.67 GB.
Which GPUs can run KAT Coder V2.5 Dev NVFP4A16?
30 consumer GPUs can run KAT Coder V2.5 Dev NVFP4A16 at Q4_K_M. Top options include AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, AMD Radeon RX 6800. 8 GPUs have plenty of headroom for comfortable inference.
Which devices can run KAT Coder V2.5 Dev NVFP4A16?
140 devices with unified memory can run KAT Coder V2.5 Dev NVFP4A16 at Q4_K_M (12.6 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.