llmrun
llm-jpLlamaForCausalLM

Llm Jp 4.1 33B Thinking — Hardware Requirements & GPU Compatibility

ChatFunctions

The llm-jp-4.1-33b-thinking model comes from the Research and Development Center for Large Language Models at Japan's National Institute of Informatics. This dense reasoning architecture uses 33 billion parameters, spans 64 layers, and underwent multi-stage pre-training before alignment via supervised fine-tuning and direct preference optimization—without reinforcement learning. It handles both Japanese and English, with documentation noting code data in several programming languages. As a dense model of this scale, it requires at least a 24 GB GPU even when quantized, or alternatively a unified-memory machine. The system supports a context window of up to 65,536 tokens. Released under the Apache 2.0 license, it allows unrestricted commercial and research use, with publication in September 2026. Within the LLM-jp-4.1 thinking series, this is the largest dense model alongside its 8B and 32B-A3B siblings, serving as an upgrade to the earlier llm-jp-4-33b-thinking variant.

33.2B params · dense66K contextApache 2.04.4K downloads17 likes703 quant downloads
B

Decent on a 24 GB GPU

Runs on24 GB Q4_K_M · ~32 tok/s · 8KMacs from24 GB IQ3_M · ~14 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Llm Jp 4.1 33B Thinking

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

Ollama
one command · needs Ollama installed
$ollama run hf.co/modulon-labs/llm-jp-4.1-33b-thinking-GGUF:Q4_K_M

Q4_K_M · needs ~24.5 GB · 16K context

Download: llm-jp-4.1-33b-thinking-Q4_K_M.gguf20.16 GBmodulon-labs

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 5090 (32 GB) (7 GB headroom) · Q4_K_M

Generation speed
~56 tok/s
generation speed
Cost per 1M output tokens
$2.66
per 1M output tokens

How Much VRAM Does Llm Jp 4.1 33B Thinking Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
15.0 GB23 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~44 tok/s
15.8 GB23.8 GB3-bit · i-quant medium — Importance-weighted 3-bit, mediumFits: 32K context · ~42 tok/s
17.0 GB25.1 GB3-bit medium — 3-bit medium quantizationFits: 16K context · ~39 tok/s
18.7 GB26.7 GB4-bit · i-quant compact — Importance-weighted 4-bit, compactFits: 16K context · ~35 tok/s
20.8 GB28.8 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 8K context · ~32 tok/s
24.5 GB32.6 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffDoes not fit: needs 28.3 GB
28.2 GB36.3 GB6-bit, very good — 6-bit quantization, very good qualityDoes not fit: needs 32 GB
34.1 GB42.1 GB8-bit, near-lossless — 8-bit quantization, near-losslessDoes not fit: needs 37.8 GB
67.3 GB75.3 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingDoes not fit: needs 71 GB
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

24.5GBat 16K context

Weights
19.9 GB
KV cache
4.3 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · fits up to 8K context · ~32 tok/s

≥50 tok/s needs ≥1.60 TB/s · RTX 5090 ~56

Which Hardware Can Run Llm Jp 4.1 33B Thinking?

Q4_K_M · 20.8 GB

Llm 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. 112 devices with unified memory can run Llm Jp 4.1 33B Thinking, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), Mac Studio M1 Max (32 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8–16 GB · RTX 4060, RTX 3060 12GB, RTX 5060 Ti 16GBDoesn't fit — smallest quant needs 18.7 GB8 GB tier →12 GB tier →16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 24.5 GB · ~32 tok/s · 8Ktight24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 24.5 GB · ~4 tok/s · 16KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 24.5 GB · ~18 tok/s · 64KMacs →

Alternatives to Llm Jp 4.1 33B Thinking

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
MiniCPM V 4.7 35B A3BOpenBMB—22.1 GB~169same size
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA—19.3 GB~197same size
Agents A1InternScience—21.5 GB~171same size
Ornith 1.0 35BDeep Reinforce—21.5 GB~171same size
EXAONE 4.5 33BLGAI-EXAONE—23.9 GB~33same size
Gemma 4 31BGoogle—21.7 GB~32same size

Specifications

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

Frequently 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)

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 ≈ 17.5 GB (at full 66K context)

VRAM usage by quantization

20.8 GB
37.4 GB

Learn more about VRAM estimation →

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_K
15.0 GB
Q3_K_M
17.0 GB
Q4_K_M ★
20.8 GB
Q5_K_M
24.5 GB
Q6_K
28.2 GB
BF16
67.3 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Llm Jp 4.1 33B Thinking on a Mac?

Yes — Mac Mini M5 Pro (24 GB) and 115 other Macs can run Llm Jp 4.1 33B Thinking, the smallest at IQ3_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 20.8 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).

Can I run Llm Jp 4.1 33B Thinking locally?

Yes — Llm Jp 4.1 33B Thinking can run locally on consumer hardware. 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/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

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. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU has plenty of headroom for comfortable inference.

Which devices can run Llm Jp 4.1 33B Thinking?

112 devices with unified memory can run Llm Jp 4.1 33B Thinking at Q4_K_M (20.8 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.