CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN — Hardware Requirements & GPU Compatibility
Chat
CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN is a 35B-parameter open language model from jcbtc. At BF16 it needs about 77.00 GB of VRAM — see which GPUs and Macs can run it below.
CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN runs on a 96 GB+ Mac or a workstation GPU
Best local pick → Mac Studio (M3 Ultra, 96GB) · BF16 · 80.9 GB · ~7 tok/s
Macs from 96 GB (BF16 · ~7 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve jcbtc/CHADROCK3.6-35B-UNCENSORED-MTP-STRIX-LEAN --max-model-len 16384 --tensor-parallel-size 8vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on H200 (141 GB) (60 GB headroom) · BF16
- Generation speed
- ~41 tok/s
- generation speed
- Cost per 1M output tokens
- $24.62
- per 1M output tokens
How Much VRAM Does CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 77 GB | 85.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on RTX PRO 6000 Blackwell Max-Q Workstation Edition 96 GB |
Selected BF16
Brain floating point 1680.9GBat 16K context
- Weights
- 76.2 GB
- KV cache
- 4.4 GB
- Overhead
- 0.3 GB
Server-class: ~80.9 GB at 16K context · one RTX PRO 6000 Blackwell Max-Q Workstation Edition 96 GB
Which Hardware Can Run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN?
BF16 · 77 GBCHADROCK3.6 35B UNCENSORED MTP STRIX LEAN (BF16) requires 77 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 101+ GB is recommended. No consumer GPU has enough memory. 30 devices with unified memory can run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 96GB).
96 GB
fits · 15.1 GB free · up to 32K ctx
3 GPUs · 2 Mac classes
RTX PRO 6000 Blackwell Max-Q Workstation Edition~15Simulate output on RTX PRO 6000 Blackwell Max-Q Workstation EditionRTX PRO 6000 Blackwell Workstation Edition~15Simulate output on RTX PRO 6000 Blackwell Workstation EditionRTX PRO 6000 Blackwell Server Edition~14Simulate output on RTX PRO 6000 Blackwell Server EditionM3 Ultra*96 GB~7Simulate output on Mac Studio (M3 Ultra, 96GB)M3 Max*96 GB~3Simulate output on MacBook Pro 14" M3 Max (96 GB)128–144 GB
fits · 47.1 GB free · up to 32K ctx
4 GPUs · 2 Mac classes · 4 device families
GH200 Grace Hopper Superchip~41Simulate output on GH200 Grace Hopper SuperchipH200 NVL~41Simulate output on H200 NVLH200 SXM~41Simulate output on H200 SXMM2 Ultra*128 GB~7Simulate output on Mac Pro M2 Ultra (128 GB)M5 Max128 GB~6Simulate output on Mac Studio M5 Max (128 GB)GB10~2Simulate output on ASUS Ascent GX10Jetson T5000 (Thor)~2Simulate output on NVIDIA Jetson AGX Thor Developer Kit
By VRAM tier · typical GPUs and Macs at BF16
Consumer GPUs (up to 32 GB) and Macs up to 64 GB: too small for this model (needs ≥ 80.9 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.6 35B A3BAlibaba | 106.8 | 22 GB | ~151 | same size |
| MiniCPM V 4.7 35B A3BOpenBMB | — | 22.1 GB | ~169 | same size |
| Ornith 1.5 35B A3Bornith-ai | — | 22 GB | ~151 | same size |
| Agents A1InternScience | — | 21.5 GB | ~171 | same size |
| Intern S2 PreviewInternLM | — | 73.2 GB | —needs > 24 GB | same size |
| EXAONE 4.5 33BLGAI-EXAONE | — | 23.9 GB | ~33 | same size |
Frequently Asked Questions
How much VRAM does CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN need?
CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN requires 77 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 35B × 16 bits ÷ 8 = 70 GB
KV Cache + Overhead ≈ 7 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.
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN?
No — CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN requires at least 77 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN on a Mac?
Yes — Mac Studio (M3 Ultra, 96GB) and 20 other Macs can run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 77 GB of usable unified memory (RAM minus macOS overhead).
Can I run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN locally?
Yes — CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN?
At BF16, CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN can reach ~62 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 ÷ 77.0 × 0.65 = ~68 tok/s
Estimated speed at BF16 (77 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN?
At BF16, the download is about 70.00 GB.
Which GPUs can run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN?
No single consumer GPU has enough VRAM to run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN at BF16 (77 GB). Multi-GPU or professional hardware is required.
Which devices can run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN?
30 devices with unified memory can run CHADROCK3.6 35B UNCENSORED MTP STRIX LEAN at BF16 (77 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (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.