Skip to content

Neural Chat 7B V3 3 VRAM requirements

How much VRAM Neural Chat 7B V3 3 needs
4-bit weights: 4.1 GBWith 8K context: 5.2 GBWith 32K context: 5.2 GB8-bit, 8K context: 8.3 GB
Parameters
7.2B
Longest context
32K
Released
Dec 2023
License
Apache 2.0
Strongest at
Not rated

How much VRAM Neural Chat 7B V3 3 needs

Memory Neural Chat 7B V3 3 needs at each precision and context length
PrecisionWeightsWith 8KWith 32K
16-bit13.5 GB14.6 GB14.6 GB
8-bit7.2 GB8.3 GB8.3 GB
6-bit5.5 GB6.7 GB6.7 GB
5-bit4.8 GB5.9 GB5.9 GB
4-bit4.1 GB5.2 GB5.2 GB
3-bit3.3 GB4.4 GB4.4 GB
2-bit2.5 GB3.7 GB3.7 GB
1.6-bit1.4 GB2.5 GB2.5 GB

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

GPUs and Macs that run Neural Chat 7B V3 3

The best way Neural Chat 7B V3 3 runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst replyReport
RTX 40606-bit32K32 tok/s1.1 sPDF: Neural Chat 7B V3 3 on RTX 4060 report
RTX 50606-bit32K51 tok/s0.8 sPDF: Neural Chat 7B V3 3 on RTX 5060 report
RTX 30706-bit32K51 tok/s0.8 sPDF: Neural Chat 7B V3 3 on RTX 3070 report
RTX 3080 10 GB8-bit32K66 tok/s0.5 sPDF: Neural Chat 7B V3 3 on RTX 3080 10 GB report
RTX 3060 12 GB8-bit32K32 tok/s1.3 sPDF: Neural Chat 7B V3 3 on RTX 3060 12 GB report
Arc B5808-bit32K29 tok/s0.9 sPDF: Neural Chat 7B V3 3 on Arc B580 report
RTX 40708-bit32K45 tok/s0.6 sPDF: Neural Chat 7B V3 3 on RTX 4070 report
RTX 4070 Super8-bit32K45 tok/s0.5 sPDF: Neural Chat 7B V3 3 on RTX 4070 Super report
RTX 50708-bit32K59 tok/s0.5 sPDF: Neural Chat 7B V3 3 on RTX 5070 report
RTX 4060 Ti 16 GB8-bit32K26 tok/s0.7 sPDF: Neural Chat 7B V3 3 on RTX 4060 Ti 16 GB report
RTX 5060 Ti 16 GB8-bit32K40 tok/s0.7 sPDF: Neural Chat 7B V3 3 on RTX 5060 Ti 16 GB report
Arc A770 16 GB8-bit32K35 tok/s0.8 sPDF: Neural Chat 7B V3 3 on Arc A770 16 GB report
Radeon RX 9070 XT8-bit32K47 tok/s0.5 sPDF: Neural Chat 7B V3 3 on Radeon RX 9070 XT report
RTX 4070 Ti Super8-bit32K59 tok/s0.4 sPDF: Neural Chat 7B V3 3 on RTX 4070 Ti Super report
RTX 4080 Super8-bit32K64 tok/s0.3 sPDF: Neural Chat 7B V3 3 on RTX 4080 Super report
RTX 5070 Ti8-bit32K77 tok/s0.4 sPDF: Neural Chat 7B V3 3 on RTX 5070 Ti report
RTX 50808-bit32K82 tok/s0.3 sPDF: Neural Chat 7B V3 3 on RTX 5080 report
Radeon RX 7900 XTX8-bit32K68 tok/s0.7 sPDF: Neural Chat 7B V3 3 on Radeon RX 7900 XTX report
RTX 30908-bit32K80 tok/s0.5 sPDF: Neural Chat 7B V3 3 on RTX 3090 report
RTX 40908-bit32K86 tok/s0.2 sPDF: Neural Chat 7B V3 3 on RTX 4090 report
Radeon AI PRO R97008-bit32K47 tok/s0.5 sPDF: Neural Chat 7B V3 3 on Radeon AI PRO R9700 report
RTX 50908-bit32K143 tok/s0.2 sPDF: Neural Chat 7B V3 3 on RTX 5090 report
2× RTX 30908-bit32K80 tok/s0.3 sPDF: Neural Chat 7B V3 3 on 2× RTX 3090 report
2× RTX 40908-bit32K86 tok/s0.1 sPDF: Neural Chat 7B V3 3 on 2× RTX 4090 report
RTX PRO 5000 Blackwell 48 GB8-bit32K111 tok/s0.2 sPDF: Neural Chat 7B V3 3 on RTX PRO 5000 Blackwell 48 GB report
RTX 6000 Ada8-bit32K82 tok/s0.2 sPDF: Neural Chat 7B V3 3 on RTX 6000 Ada report
L40S8-bit32K74 tok/s0.3 sPDF: Neural Chat 7B V3 3 on L40S report
2× RTX 50908-bit32K143 tok/s0.1 sPDF: Neural Chat 7B V3 3 on 2× RTX 5090 report
4× RTX 30908-bit32K80 tok/s0.1 sPDF: Neural Chat 7B V3 3 on 4× RTX 3090 report
RTX PRO 6000 Blackwell8-bit32K143 tok/s0.1 sPDF: Neural Chat 7B V3 3 on RTX PRO 6000 Blackwell report
Mac mini M4 16 GB8-bit32K13 tok/s10 sPDF: Neural Chat 7B V3 3 on Mac mini M4 16 GB report
Mac mini M4 24 GB8-bit32K13 tok/s10 sPDF: Neural Chat 7B V3 3 on Mac mini M4 24 GB report
Mac mini M4 32 GB8-bit32K13 tok/s10 sPDF: Neural Chat 7B V3 3 on Mac mini M4 32 GB report
Mac mini M4 Pro 24 GB8-bit32K28 tok/s5.1 sPDF: Neural Chat 7B V3 3 on Mac mini M4 Pro 24 GB report
Mac mini M4 Pro 48 GB8-bit32K28 tok/s5.1 sPDF: Neural Chat 7B V3 3 on Mac mini M4 Pro 48 GB report
Mac mini M4 Pro 64 GB8-bit32K28 tok/s5.1 sPDF: Neural Chat 7B V3 3 on Mac mini M4 Pro 64 GB report
M4 Max 128 GB8-bit32K48 tok/s2.6 sPDF: Neural Chat 7B V3 3 on M4 Max 128 GB report
M5 Max 128 GB8-bit32K53 tok/s0.7 sPDF: Neural Chat 7B V3 3 on M5 Max 128 GB report
M3 Ultra 96 GB8-bit32K60 tok/s1.4 sPDF: Neural Chat 7B V3 3 on M3 Ultra 96 GB report
M3 Ultra 256 GB8-bit32K60 tok/s1.4 sPDF: Neural Chat 7B V3 3 on M3 Ultra 256 GB report
M3 Ultra 512 GB8-bit32K60 tok/s1.4 sPDF: Neural Chat 7B V3 3 on M3 Ultra 512 GB report
M5 Ultra 512 GB8-bit32K82 tok/s0.5 sPDF: Neural Chat 7B V3 3 on M5 Ultra 512 GB report
Ryzen AI Max+ 395 64 GB8-bit32K20 tok/s1.5 sPDF: Neural Chat 7B V3 3 on Ryzen AI Max+ 395 64 GB report
Ryzen AI Max+ 395 128 GB8-bit32K20 tok/s1.5 sPDF: Neural Chat 7B V3 3 on Ryzen AI Max+ 395 128 GB report
RTX Spark8-bit32K27 tok/s0.5 sPDF: Neural Chat 7B V3 3 on RTX Spark report
DGX Spark8-bit32K25 tok/s0.5 sPDF: Neural Chat 7B V3 3 on DGX Spark report
Dual DGX Spark8-bit32K25 tok/s0.3 sPDF: Neural Chat 7B V3 3 on Dual DGX Spark report
DGX Station GB3008-bit32K403 tok/s0.1 sPDF: Neural Chat 7B V3 3 on DGX Station GB300 report
2× RTX PRO 6000 Blackwell8-bit32K143 tok/s0.1 sPDF: Neural Chat 7B V3 3 on 2× RTX PRO 6000 Blackwell report
4× RTX PRO 6000 Blackwell8-bit32K143 tok/s0.1 sPDF: Neural Chat 7B V3 3 on 4× RTX PRO 6000 Blackwell report
8× RTX PRO 6000 Blackwell8-bit32K143 tok/s0.1 sPDF: Neural Chat 7B V3 3 on 8× RTX PRO 6000 Blackwell report
A100 80 GB SXM8-bit32K160 tok/s0.3 sPDF: Neural Chat 7B V3 3 on A100 80 GB SXM report
H100 SXM8-bit32K239 tok/s0.1 sPDF: Neural Chat 7B V3 3 on H100 SXM report
4× H200 NVL8-bit32K312 tok/s0.1 sPDF: Neural Chat 7B V3 3 on 4× H200 NVL report
8× H200 NVL8-bit32K312 tok/s0.1 sPDF: Neural Chat 7B V3 3 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 mradermacher/neural-chat-7b-v3-3-GGUF
vLLM
vllm serve Intel/neural-chat-7b-v3-3

Questions

How much VRAM does Neural Chat 7B V3 3 need?

Neural Chat 7B V3 3 needs 4.1 GB for its weights at 4-bit, 5.2 GB with an 8K context and 5.2 GB with 32K. At 8-bit, 8.3 GB.

What is the minimum VRAM for Neural Chat 7B V3 3?

About 4.4 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 Neural Chat 7B V3 3?

7.2B parameters: 13.5 GB of weights at 16-bit, 4.1 GB at 4-bit.

Can Neural Chat 7B V3 3 run on an RTX 4090?

Yes. At 8-bit it holds 32K of context and writes about 86 tokens a second.

More models