Llm Jp 4.1 32B A3b Thinking — Hardware Requirements & GPU Compatibility
Chat
llm-jp-4.1-32b-a3b-thinking is a Mixture-of-Experts reasoning model from the Research and Development Center for Large Language Models at Japan's National Institute of Informatics, with 32 billion total and 3.8 billion active parameters. It uses 128 routed experts with 8 active, was pre-trained and mid-trained on 11.7 trillion tokens, and was post-trained 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. Only 3.8 billion parameters are active per token, so decoding is fast, but the full weights still need a large GPU or a 32 GB-class unified-memory machine even when quantized. 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 MoE member of the LLM-jp-4.1 thinking series alongside 8B and 33B dense models, and an update to the earlier llm-jp-4 version.
639 downloads
19 likesSpecifications
- Publisher
- llm-jp
- Parameters
- 32.1B
- Architecture
- Qwen3MoeForCausalLM
- 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 32B A3b Thinking Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 14.0 GB | 16.1 GB | 13.66 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 16.0 GB | 18.1 GB | 15.67 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 19.6 GB | 21.7 GB | 19.28 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 23.3 GB | 25.4 GB | 22.90 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 26.9 GB | 29.0 GB | 26.51 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 32.5 GB | 34.6 GB | 32.14 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 64.7 GB | 66.7 GB | 64.28 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 32B A3b Thinking?
Q4_K_M · 19.6 GBLlm Jp 4.1 32B A3b Thinking (Q4_K_M) requires 19.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ GB is recommended. Using the full 66K context window can add up to 2.1 GB, bringing total usage to 21.7 GB. 8 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 32B A3b Thinking?
Q4_K_M · 19.6 GB41 devices with unified memory can run Llm Jp 4.1 32B A3b 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 32B A3b Thinking need?
Llm Jp 4.1 32B A3b Thinking requires 19.6 GB of VRAM at Q4_K_M, or 64.7 GB at BF16. Full 66K context adds up to 2.1 GB (21.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32.1B × 4.8 bits ÷ 8 = 19.3 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 2.4 GB (at full 66K context)
VRAM usage by quantization
Q4_K_M19.6 GBQ4_K_M + full context21.7 GB- Can NVIDIA GeForce RTX 4090 run Llm Jp 4.1 32B A3b Thinking?
Yes, at Q5_K_M (23.3 GB) or lower. Higher quantizations like Q6_K (26.9 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Llm Jp 4.1 32B A3b Thinking?
For Llm Jp 4.1 32B A3b Thinking, Q4_K_M (19.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (23.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 14.0 GB.
VRAM requirement by quantization
Q2_K14.0 GBQ4_K_M ★19.6 GBQ5_K_M23.3 GBQ6_K26.9 GBQ8_032.5 GBBF1664.7 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Llm Jp 4.1 32B A3b Thinking on a Mac?
Llm Jp 4.1 32B A3b Thinking requires at least 14.0 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 32B A3b Thinking locally?
Yes — Llm Jp 4.1 32B A3b Thinking can run locally on consumer hardware. At Q4_K_M quantization it needs 19.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Llm Jp 4.1 32B A3b Thinking?
At Q4_K_M, Llm Jp 4.1 32B A3b Thinking can reach ~145 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~188 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 ÷ 19.6 × 0.65 = ~453 tok/s
Estimated speed at Q4_K_M (19.6 GB)
~453 tok/s~188 tok/s~453 tok/s~401 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 32B A3b Thinking?
At Q4_K_M, the download is about 19.28 GB. The full-precision BF16 version is 64.28 GB. The smallest option (Q2_K) is 13.66 GB.
- Which GPUs can run Llm Jp 4.1 32B A3b Thinking?
8 consumer GPUs can run Llm Jp 4.1 32B A3b Thinking at Q4_K_M (19.6 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Llm Jp 4.1 32B A3b Thinking?
41 devices with unified memory can run Llm Jp 4.1 32B A3b Thinking at Q4_K_M (19.6 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.