Skip to content

Llm Jp 4 8B Base VRAM requirements

How much VRAM Llm Jp 4 8B Base needs
4-bit weights: 4.9 GBWith 8K context: 6.8 GBWith 32K context: 9.8 GB8-bit, 8K context: 10.5 GB
Parameters
8.6B
Longest context
64K
Released
Mar 2026
License
Apache 2.0
Strongest at
Not rated

How much VRAM Llm Jp 4 8B Base needs

Memory Llm Jp 4 8B Base needs at each precision and context length
PrecisionWeightsWith 8KWith 32KWith 64K
16-bit16.0 GB18.0 GB21.0 GB25.0 GB
8-bit8.5 GB10.5 GB13.5 GB17.5 GB
6-bit6.6 GB8.5 GB11.5 GB15.5 GB
5-bit5.7 GB7.6 GB10.6 GB14.6 GB
4-bit4.9 GB6.8 GB9.8 GB13.8 GB
3-bit3.9 GB5.9 GB8.9 GB12.9 GB
2-bit3.0 GB5.0 GB8.0 GB12.0 GB
1.6-bit1.7 GB3.6 GB6.6 GB10.6 GB

One conversation, 16-bit context cache, runtime overhead included.

GPUs and Macs that run Llm Jp 4 8B Base

The best way Llm Jp 4 8B Base runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst replyReport
RTX 40603-bit20K48 tok/s1.0 sPDF: Llm Jp 4 8B Base on RTX 4060 report
RTX 50603-bit20K76 tok/s0.8 sPDF: Llm Jp 4 8B Base on RTX 5060 report
RTX 30703-bit20K76 tok/s0.8 sPDF: Llm Jp 4 8B Base on RTX 3070 report
RTX 3080 10 GB5-bit20K88 tok/s0.5 sPDF: Llm Jp 4 8B Base on RTX 3080 10 GB report
RTX 3060 12 GB6-bit28K38 tok/s1.2 sPDF: Llm Jp 4 8B Base on RTX 3060 12 GB report
Arc B5806-bit28K33 tok/s0.8 sPDF: Llm Jp 4 8B Base on Arc B580 report
RTX 40706-bit28K52 tok/s0.5 sPDF: Llm Jp 4 8B Base on RTX 4070 report
RTX 4070 Super6-bit28K52 tok/s0.4 sPDF: Llm Jp 4 8B Base on RTX 4070 Super report
RTX 50706-bit28K69 tok/s0.5 sPDF: Llm Jp 4 8B Base on RTX 5070 report
RTX 4060 Ti 16 GB8-bit44K24 tok/s0.7 sPDF: Llm Jp 4 8B Base on RTX 4060 Ti 16 GB report
RTX 5060 Ti 16 GB8-bit44K37 tok/s0.7 sPDF: Llm Jp 4 8B Base on RTX 5060 Ti 16 GB report
Arc A770 16 GB8-bit44K32 tok/s0.8 sPDF: Llm Jp 4 8B Base on Arc A770 16 GB report
Radeon RX 9070 XT8-bit44K43 tok/s0.4 sPDF: Llm Jp 4 8B Base on Radeon RX 9070 XT report
RTX 4070 Ti Super8-bit44K54 tok/s0.4 sPDF: Llm Jp 4 8B Base on RTX 4070 Ti Super report
RTX 4080 Super8-bit44K59 tok/s0.3 sPDF: Llm Jp 4 8B Base on RTX 4080 Super report
RTX 5070 Ti8-bit44K71 tok/s0.4 sPDF: Llm Jp 4 8B Base on RTX 5070 Ti report
RTX 50808-bit44K75 tok/s0.3 sPDF: Llm Jp 4 8B Base on RTX 5080 report
Radeon RX 7900 XTX8-bit64K63 tok/s0.7 sPDF: Llm Jp 4 8B Base on Radeon RX 7900 XTX report
RTX 30908-bit64K74 tok/s0.4 sPDF: Llm Jp 4 8B Base on RTX 3090 report
RTX 40908-bit64K79 tok/s0.2 sPDF: Llm Jp 4 8B Base on RTX 4090 report
Radeon AI PRO R97008-bit64K43 tok/s0.4 sPDF: Llm Jp 4 8B Base on Radeon AI PRO R9700 report
RTX 50908-bit64K132 tok/s0.1 sPDF: Llm Jp 4 8B Base on RTX 5090 report
2× RTX 30908-bit64K74 tok/s0.3 sPDF: Llm Jp 4 8B Base on 2× RTX 3090 report
2× RTX 40908-bit64K79 tok/s0.1 sPDF: Llm Jp 4 8B Base on 2× RTX 4090 report
RTX PRO 5000 Blackwell 48 GB8-bit64K103 tok/s0.2 sPDF: Llm Jp 4 8B Base on RTX PRO 5000 Blackwell 48 GB report
RTX 6000 Ada8-bit64K75 tok/s0.2 sPDF: Llm Jp 4 8B Base on RTX 6000 Ada report
L40S8-bit64K68 tok/s0.3 sPDF: Llm Jp 4 8B Base on L40S report
2× RTX 50908-bit64K132 tok/s0.1 sPDF: Llm Jp 4 8B Base on 2× RTX 5090 report
4× RTX 30908-bit64K74 tok/s0.1 sPDF: Llm Jp 4 8B Base on 4× RTX 3090 report
RTX PRO 6000 Blackwell8-bit64K132 tok/s0.1 sPDF: Llm Jp 4 8B Base on RTX PRO 6000 Blackwell report
Mac mini M4 16 GB6-bit20K15 tok/s9.9 sPDF: Llm Jp 4 8B Base on Mac mini M4 16 GB report
Mac mini M4 24 GB8-bit44K12 tok/s9.9 sPDF: Llm Jp 4 8B Base on Mac mini M4 24 GB report
Mac mini M4 32 GB8-bit64K12 tok/s9.9 sPDF: Llm Jp 4 8B Base on Mac mini M4 32 GB report
Mac mini M4 Pro 24 GB8-bit44K25 tok/s5.0 sPDF: Llm Jp 4 8B Base on Mac mini M4 Pro 24 GB report
Mac mini M4 Pro 48 GB8-bit64K25 tok/s5.0 sPDF: Llm Jp 4 8B Base on Mac mini M4 Pro 48 GB report
Mac mini M4 Pro 64 GB8-bit64K25 tok/s5.0 sPDF: Llm Jp 4 8B Base on Mac mini M4 Pro 64 GB report
M4 Max 128 GB8-bit64K44 tok/s2.5 sPDF: Llm Jp 4 8B Base on M4 Max 128 GB report
M5 Max 128 GB8-bit64K49 tok/s0.7 sPDF: Llm Jp 4 8B Base on M5 Max 128 GB report
M3 Ultra 96 GB8-bit64K55 tok/s1.4 sPDF: Llm Jp 4 8B Base on M3 Ultra 96 GB report
M3 Ultra 256 GB8-bit64K55 tok/s1.4 sPDF: Llm Jp 4 8B Base on M3 Ultra 256 GB report
M3 Ultra 512 GB8-bit64K55 tok/s1.4 sPDF: Llm Jp 4 8B Base on M3 Ultra 512 GB report
M5 Ultra 512 GB8-bit64K76 tok/s0.4 sPDF: Llm Jp 4 8B Base on M5 Ultra 512 GB report
Ryzen AI Max+ 395 64 GB8-bit64K18 tok/s1.4 sPDF: Llm Jp 4 8B Base on Ryzen AI Max+ 395 64 GB report
Ryzen AI Max+ 395 128 GB8-bit64K18 tok/s1.4 sPDF: Llm Jp 4 8B Base on Ryzen AI Max+ 395 128 GB report
RTX Spark8-bit64K25 tok/s0.5 sPDF: Llm Jp 4 8B Base on RTX Spark report
DGX Spark8-bit64K23 tok/s0.5 sPDF: Llm Jp 4 8B Base on DGX Spark report
Dual DGX Spark8-bit64K23 tok/s0.3 sPDF: Llm Jp 4 8B Base on Dual DGX Spark report
DGX Station GB3008-bit64K381 tok/s0.1 sPDF: Llm Jp 4 8B Base on DGX Station GB300 report
2× RTX PRO 6000 Blackwell8-bit64K132 tok/s0.1 sPDF: Llm Jp 4 8B Base on 2× RTX PRO 6000 Blackwell report
4× RTX PRO 6000 Blackwell8-bit64K132 tok/s0.1 sPDF: Llm Jp 4 8B Base on 4× RTX PRO 6000 Blackwell report
8× RTX PRO 6000 Blackwell8-bit64K132 tok/s0.1 sPDF: Llm Jp 4 8B Base on 8× RTX PRO 6000 Blackwell report
A100 80 GB SXM8-bit64K148 tok/s0.3 sPDF: Llm Jp 4 8B Base on A100 80 GB SXM report
H100 SXM8-bit64K223 tok/s0.1 sPDF: Llm Jp 4 8B Base on H100 SXM report
4× H200 NVL8-bit64K292 tok/s0.1 sPDF: Llm Jp 4 8B Base on 4× H200 NVL report
8× H200 NVL8-bit64K292 tok/s0.1 sPDF: Llm Jp 4 8B Base on 8× H200 NVL report

Best fit is the highest quality, up to 8-bit, that leaves 16K of context. First reply is the wait for a 2K prompt. Speeds are rough, plus or minus 25%.

How to run it

llama.cpp
llama-server -hf kukutan/genpatsu-ai-8b-GGUF
vLLM
vllm serve llm-jp/llm-jp-4-8b-base

Questions

How much VRAM does Llm Jp 4 8B Base need?

Llm Jp 4 8B Base needs 4.9 GB for its weights at 4-bit, 6.8 GB with an 8K context and 9.8 GB with 32K. At 8-bit, 10.5 GB.

What is the minimum VRAM for Llm Jp 4 8B Base?

About 5.9 GB at 3-bit with an 8K context, the lowest precision we recommend for a model this size. The smallest machine here that runs it without spilling is the RTX 4060.

How big is Llm Jp 4 8B Base?

8.6B parameters: 16.0 GB of weights at 16-bit, 4.9 GB at 4-bit.

Can Llm Jp 4 8B Base run on an RTX 4090?

Yes. At 8-bit it holds 64K of context and writes about 79 tokens a second.

More models