Only with CPU offload
LLM-jp 4 33B Thinking at Q4_K_M needs 21.3 GB but only 14.4 GB is addressable, so about 37% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 4.7 tokens per second — usable for batch work, painful for chat.
Japan’s national-institute reasoning model, Japanese and English. A plain dense Llama-style 33B: Q4 is a tight 24 GB fit.
Hardware requirements What hardware do I need to run LLM-jp 4 33B Thinking? →At Q4_K_M with an 8K context: a 32 GB GPU (RTX 5090) or a 36 GB Mac (M4 Max). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 32.9 GB | 35.5 GB | — | ~1.7 | −0.1% ppl | 21.1 GB over |
| Q6_K | 25.4 GB | 28.0 GB | — | ~2.5 | −0.4% ppl | 13.6 GB over |
| Q5_K_M | 21.9 GB | 24.5 GB | — | ~3.3 | −0.8% ppl | 10.1 GB over |
| Q4_K_M | 18.7 GB | 21.3 GB | — | ~4.7 | −1.9% ppl | 6.9 GB over |
| Q3_K_M | 15.1 GB | 17.7 GB | — | ~8.9 | −5.4% ppl | 3.3 GB over |
| Q2_K | 12.9 GB | 15.5 GB | 3K | ~19 | −15% ppl | 1.1 GB over |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.
How to run it
$ llama-server \
-hf llm-jp/llm-jp-4-33b-thinking:Q4_K_M \
-c 8192 -ngl 40
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a GeForce RTX 5070 Ti
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | ~4.9 | CPU offload |
| DeepSeek-R1-Distill-Qwen 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | ~4.9 | CPU offload |
| Qwen2.5-Coder 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | ~4.9 | CPU offload |
| Olmo 3.1 32B Instruct 32.2B · similar size |
Q4_K_M · 20.0 GB | ~5.7 | CPU offload |
| Nemotron 3.5 Lightning 30B-A3B 31.6B MoE · similar size |
Q4_K_M · 18.4 GB | ~28 | CPU offload |
| Gemma 4 31B 31.3B · similar size |
Q4_K_M · 20.2 GB | ~5.5 | CPU offload |
| GLM-4.7-Flash 30B-A3B 31.2B MoE · similar size |
Q4_K_M · 18.6 GB | ~29 | CPU offload |
LLM-jp 4 33B Thinking on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
21.3 GB | ~2.4 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
21.3 GB | ~3.0 | CPU offload |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
21.3 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
21.3 GB | 33 | Tight fit |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
21.3 GB | 31 | Tight fit |
| GeForce RTX 5090 30.4 GB usable · 1792 GB/s |
21.3 GB | 58 | Runs great |
| M4 Max · 36 GB 27.0 GB usable · 410 GB/s |
21.3 GB | 12 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
21.3 GB | 12 | Runs great |