Skip to content

OTel 2.0 LLM 31B IT VRAM requirements

How much VRAM OTel 2.0 LLM 31B IT needs
4-bit weights: 17.7 GBWith 8K context: 19.9 GBWith 32K context: 20.8 GB8-bit, 8K context: 33.2 GB
Parameters
31.3B
Longest context
256K
Released
Jul 2026
License
Apache 2.0
Strongest at
Not rated

How much VRAM OTel 2.0 LLM 31B IT needs

Memory OTel 2.0 LLM 31B IT needs at each precision and context length
PrecisionWeightsWith 8KWith 32KWith 128K
16-bit58.3 GB60.5 GB61.4 GB65.1 GB
8-bit30.9 GB33.2 GB34.1 GB37.8 GB
6-bit23.9 GB26.1 GB27.0 GB30.8 GB
5-bit20.7 GB22.9 GB23.9 GB27.6 GB
4-bit17.7 GB19.9 GB20.8 GB24.6 GB
3-bit14.2 GB16.4 GB17.4 GB21.1 GB
2-bit10.9 GB13.1 GB14.1 GB17.8 GB
1.6-bit6.0 GB8.2 GB9.2 GB12.9 GB

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

GPUs and Macs that run OTel 2.0 LLM 31B IT

The best way OTel 2.0 LLM 31B IT runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst replyReport
RTX 4060Too bigPDF: OTel 2.0 LLM 31B IT on RTX 4060 report
RTX 5060Too bigPDF: OTel 2.0 LLM 31B IT on RTX 5060 report
RTX 3070Too bigPDF: OTel 2.0 LLM 31B IT on RTX 3070 report
RTX 3080 10 GBToo bigPDF: OTel 2.0 LLM 31B IT on RTX 3080 10 GB report
RTX 3060 12 GBToo bigPDF: OTel 2.0 LLM 31B IT on RTX 3060 12 GB report
Arc B580Too bigPDF: OTel 2.0 LLM 31B IT on Arc B580 report
RTX 4070Too bigPDF: OTel 2.0 LLM 31B IT on RTX 4070 report
RTX 4070 SuperToo bigPDF: OTel 2.0 LLM 31B IT on RTX 4070 Super report
RTX 5070Too bigPDF: OTel 2.0 LLM 31B IT on RTX 5070 report
RTX 4060 Ti 16 GBToo bigPDF: OTel 2.0 LLM 31B IT on RTX 4060 Ti 16 GB report
RTX 5060 Ti 16 GBToo bigPDF: OTel 2.0 LLM 31B IT on RTX 5060 Ti 16 GB report
Arc A770 16 GBToo bigPDF: OTel 2.0 LLM 31B IT on Arc A770 16 GB report
Radeon RX 9070 XTToo bigPDF: OTel 2.0 LLM 31B IT on Radeon RX 9070 XT report
RTX 4070 Ti SuperToo bigPDF: OTel 2.0 LLM 31B IT on RTX 4070 Ti Super report
RTX 4080 SuperToo bigPDF: OTel 2.0 LLM 31B IT on RTX 4080 Super report
RTX 5070 TiToo bigPDF: OTel 2.0 LLM 31B IT on RTX 5070 Ti report
RTX 5080Too bigPDF: OTel 2.0 LLM 31B IT on RTX 5080 report
Radeon RX 7900 XTX4-bit80K28 tok/s2.9 sPDF: OTel 2.0 LLM 31B IT on Radeon RX 7900 XTX report
RTX 30904-bit80K33 tok/s1.9 sPDF: OTel 2.0 LLM 31B IT on RTX 3090 report
RTX 40904-bit80K35 tok/s0.8 sPDF: OTel 2.0 LLM 31B IT on RTX 4090 report
Radeon AI PRO R97006-bit112K14 tok/s1.9 sPDF: OTel 2.0 LLM 31B IT on Radeon AI PRO R9700 report
RTX 50906-bit112K45 tok/s0.6 sPDF: OTel 2.0 LLM 31B IT on RTX 5090 report
2× RTX 30908-bit256K19 tok/s1.1 sPDF: OTel 2.0 LLM 31B IT on 2× RTX 3090 report
2× RTX 40908-bit256K20 tok/s0.5 sPDF: OTel 2.0 LLM 31B IT on 2× RTX 4090 report
RTX PRO 5000 Blackwell 48 GB8-bit256K27 tok/s1.0 sPDF: OTel 2.0 LLM 31B IT on RTX PRO 5000 Blackwell 48 GB report
RTX 6000 Ada8-bit256K20 tok/s0.7 sPDF: OTel 2.0 LLM 31B IT on RTX 6000 Ada report
L40S8-bit256K18 tok/s1.2 sPDF: OTel 2.0 LLM 31B IT on L40S report
2× RTX 50908-bit256K35 tok/s0.4 sPDF: OTel 2.0 LLM 31B IT on 2× RTX 5090 report
4× RTX 30908-bit256K19 tok/s0.6 sPDF: OTel 2.0 LLM 31B IT on 4× RTX 3090 report
RTX PRO 6000 Blackwell8-bit256K35 tok/s0.5 sPDF: OTel 2.0 LLM 31B IT on RTX PRO 6000 Blackwell report
Mac mini M4 16 GBToo bigPDF: OTel 2.0 LLM 31B IT on Mac mini M4 16 GB report
Mac mini M4 24 GBToo bigPDF: OTel 2.0 LLM 31B IT on Mac mini M4 24 GB report
Mac mini M4 32 GB4-bit20K5.1 tok/s42 sPDF: OTel 2.0 LLM 31B IT on Mac mini M4 32 GB report
Mac mini M4 Pro 24 GBToo bigPDF: OTel 2.0 LLM 31B IT on Mac mini M4 Pro 24 GB report
Mac mini M4 Pro 48 GB8-bit36K6.5 tok/s21 sPDF: OTel 2.0 LLM 31B IT on Mac mini M4 Pro 48 GB report
Mac mini M4 Pro 64 GB8-bit256K6.5 tok/s21 sPDF: OTel 2.0 LLM 31B IT on Mac mini M4 Pro 64 GB report
M4 Max 128 GB8-bit256K12 tok/s10 sPDF: OTel 2.0 LLM 31B IT on M4 Max 128 GB report
M5 Max 128 GB8-bit256K13 tok/s3.0 sPDF: OTel 2.0 LLM 31B IT on M5 Max 128 GB report
M3 Ultra 96 GB8-bit256K15 tok/s5.9 sPDF: OTel 2.0 LLM 31B IT on M3 Ultra 96 GB report
M3 Ultra 256 GB8-bit256K15 tok/s5.9 sPDF: OTel 2.0 LLM 31B IT on M3 Ultra 256 GB report
M3 Ultra 512 GB8-bit256K15 tok/s5.9 sPDF: OTel 2.0 LLM 31B IT on M3 Ultra 512 GB report
M5 Ultra 512 GB8-bit256K21 tok/s1.8 sPDF: OTel 2.0 LLM 31B IT on M5 Ultra 512 GB report
Ryzen AI Max+ 395 64 GB8-bit256K4.6 tok/s6.0 sPDF: OTel 2.0 LLM 31B IT on Ryzen AI Max+ 395 64 GB report
Ryzen AI Max+ 395 128 GB8-bit256K4.6 tok/s6.0 sPDF: OTel 2.0 LLM 31B IT on Ryzen AI Max+ 395 128 GB report
RTX Spark8-bit256K6.2 tok/s2.1 sPDF: OTel 2.0 LLM 31B IT on RTX Spark report
DGX Spark8-bit256K5.7 tok/s2.1 sPDF: OTel 2.0 LLM 31B IT on DGX Spark report
Dual DGX Spark8-bit256K5.7 tok/s1.2 sPDF: OTel 2.0 LLM 31B IT on Dual DGX Spark report
DGX Station GB3008-bit256K118 tok/s0.2 sPDF: OTel 2.0 LLM 31B IT on DGX Station GB300 report
2× RTX PRO 6000 Blackwell8-bit256K35 tok/s0.3 sPDF: OTel 2.0 LLM 31B IT on 2× RTX PRO 6000 Blackwell report
4× RTX PRO 6000 Blackwell8-bit256K35 tok/s0.2 sPDF: OTel 2.0 LLM 31B IT on 4× RTX PRO 6000 Blackwell report
8× RTX PRO 6000 Blackwell8-bit256K35 tok/s0.1 sPDF: OTel 2.0 LLM 31B IT on 8× RTX PRO 6000 Blackwell report
A100 80 GB SXM8-bit256K40 tok/s1.3 sPDF: OTel 2.0 LLM 31B IT on A100 80 GB SXM report
H100 SXM8-bit256K63 tok/s0.4 sPDF: OTel 2.0 LLM 31B IT on H100 SXM report
4× H200 NVL8-bit256K86 tok/s0.2 sPDF: OTel 2.0 LLM 31B IT on 4× H200 NVL report
8× H200 NVL8-bit256K86 tok/s0.1 sPDF: OTel 2.0 LLM 31B IT 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 wfakhri/OTel-2.0-LLM-31B-IT-GGUF
vLLM
vllm serve farbodtavakkoli/OTel-2.0-LLM-31B-IT

Questions

How much VRAM does OTel 2.0 LLM 31B IT need?

OTel 2.0 LLM 31B IT needs 17.7 GB for its weights at 4-bit, 19.9 GB with an 8K context and 20.8 GB with 32K. At 8-bit, 33.2 GB.

What is the minimum VRAM for OTel 2.0 LLM 31B IT?

About 16.4 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 Radeon RX 7900 XTX.

How big is OTel 2.0 LLM 31B IT?

31.3B parameters: 58.3 GB of weights at 16-bit, 17.7 GB at 4-bit.

Can OTel 2.0 LLM 31B IT run on an RTX 4090?

Yes. At 4-bit it holds 80K of context and writes about 35 tokens a second.

More models