Llm Jp 4.1 33B Thinking — Hardware Requirements & GPU Compatibility
Chat
llm-jp-4.1-33b-thinking is a 33-billion-parameter dense reasoning model from the Research and Development Center for Large Language Models at Japan's National Institute of Informatics. It has 64 layers, was pre-trained and mid-trained on a multi-stage pipeline, and was then aligned with supervised fine-tuning and direct preference optimization without reinforcement learning. It targets Japanese and English, and the card notes code data in several programming languages. As a dense model of this size, it needs a 24 GB or larger GPU even when quantized, or a unified-memory machine. The model supports a 65,536 token context window. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in September 2026. It is the largest dense model in the LLM-jp-4.1 thinking series, alongside 8B and 32B-A3B siblings, and an update to the earlier llm-jp-4-33b-thinking.
609 downloads
11 likesSpecifications
- Publisher
- llm-jp
- Parameters
- 33.2B
- Architecture
- LlamaForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 196,608
- Release Date
- 2026-09-16
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Llm Jp 4.1 33B Thinking Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 15.0 GB | 31.6 GB | 14.12 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 17.0 GB | 33.7 GB | 16.19 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 20.8 GB | 37.4 GB | 19.93 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 24.5 GB | 41.1 GB | 23.67 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 28.2 GB | 44.9 GB | 27.41 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 34.1 GB | 50.7 GB | 33.22 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 67.3 GB | 83.9 GB | 66.44 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 Llm Jp 4.1 33B Thinking?
Q4_K_M · 20.8 GBLlm Jp 4.1 33B Thinking (Q4_K_M) requires 20.8 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 66K context window can add up to 16.6 GB, bringing total usage to 37.4 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 Llm Jp 4.1 33B Thinking?
Q4_K_M · 20.8 GB41 devices with unified memory can run Llm Jp 4.1 33B Thinking, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightFrequently Asked Questions
- How much VRAM does Llm Jp 4.1 33B Thinking need?
Llm Jp 4.1 33B Thinking requires 20.8 GB of VRAM at Q4_K_M, or 67.3 GB at BF16. Full 66K context adds up to 16.6 GB (37.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 33.2B × 4.8 bits ÷ 8 = 19.9 GB
KV Cache + Overhead ≈ 0.9 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 17.5 GB (at full 66K context)
VRAM usage by quantization
Q4_K_M20.8 GBQ4_K_M + full context37.4 GB- Can NVIDIA GeForce RTX 4090 run Llm Jp 4.1 33B Thinking?
Yes, at Q4_K_M (20.8 GB) or lower. Higher quantizations like Q5_K_M (24.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Llm Jp 4.1 33B Thinking?
For Llm Jp 4.1 33B Thinking, Q4_K_M (20.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (24.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 15.0 GB.
VRAM requirement by quantization
Q2_K15.0 GBQ4_K_M ★20.8 GBQ5_K_M24.5 GBQ6_K28.2 GBQ8_034.1 GBBF1667.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Llm Jp 4.1 33B Thinking on a Mac?
Llm Jp 4.1 33B Thinking requires at least 15.0 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 Llm Jp 4.1 33B Thinking locally?
Yes — Llm Jp 4.1 33B Thinking can run locally on consumer hardware. At Q4_K_M quantization it needs 20.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Llm Jp 4.1 33B Thinking?
At Q4_K_M, Llm Jp 4.1 33B Thinking can reach ~231 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~32 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 ÷ 20.8 × 0.65 = ~250 tok/s
Estimated speed at Q4_K_M (20.8 GB)
~250 tok/s~32 tok/s~250 tok/s~231 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Llm Jp 4.1 33B Thinking?
At Q4_K_M, the download is about 19.93 GB. The full-precision BF16 version is 66.44 GB. The smallest option (Q2_K) is 14.12 GB.
- Which GPUs can run Llm Jp 4.1 33B Thinking?
7 consumer GPUs can run Llm Jp 4.1 33B Thinking at Q4_K_M (20.8 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 Llm Jp 4.1 33B Thinking?
41 devices with unified memory can run Llm Jp 4.1 33B Thinking at Q4_K_M (20.8 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.