Skip to content

Llama xLAM 2 8B Fc R VRAM requirements

How much VRAM Llama xLAM 2 8B Fc R needs
4-bit weights: 4.5 GBWith 8K context: 6.4 GBWith 32K context: 9.4 GB8-bit, 8K context: 9.8 GB
Parameters
8B
Longest context
128K
Released
Mar 2025
License
CC BY-NC 4.0
Strongest at
Not rated

Its licence (CC BY-NC 4.0) is not a standard open-source one: check the terms before commercial use.

How much VRAM Llama xLAM 2 8B Fc R needs

Memory Llama xLAM 2 8B Fc R needs at each precision and context length
PrecisionWeightsWith 8KWith 32KWith 128K
16-bit15.0 GB16.8 GB19.8 GB31.8 GB
8-bit7.9 GB9.8 GB12.8 GB24.8 GB
6-bit6.1 GB8.0 GB11.0 GB23.0 GB
5-bit5.3 GB7.1 GB10.1 GB22.1 GB
4-bit4.5 GB6.4 GB9.4 GB21.4 GB
3-bit3.7 GB5.5 GB8.5 GB20.5 GB
2-bit2.8 GB4.6 GB7.6 GB19.6 GB
1.6-bit1.5 GB3.4 GB6.4 GB18.4 GB

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

GPUs and Macs that run Llama xLAM 2 8B Fc R

The best way Llama xLAM 2 8B Fc R runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst replyReport
RTX 40604-bit16K40 tok/s1.0 sPDF: Llama xLAM 2 8B Fc R on RTX 4060 report
RTX 50604-bit16K65 tok/s0.8 sPDF: Llama xLAM 2 8B Fc R on RTX 5060 report
RTX 30704-bit16K65 tok/s0.8 sPDF: Llama xLAM 2 8B Fc R on RTX 3070 report
RTX 3080 10 GB6-bit20K80 tok/s0.5 sPDF: Llama xLAM 2 8B Fc R on RTX 3080 10 GB report
RTX 3060 12 GB8-bit20K31 tok/s1.2 sPDF: Llama xLAM 2 8B Fc R on RTX 3060 12 GB report
Arc B5808-bit20K27 tok/s0.8 sPDF: Llama xLAM 2 8B Fc R on Arc B580 report
RTX 40708-bit20K42 tok/s0.5 sPDF: Llama xLAM 2 8B Fc R on RTX 4070 report
RTX 4070 Super8-bit20K42 tok/s0.4 sPDF: Llama xLAM 2 8B Fc R on RTX 4070 Super report
RTX 50708-bit20K56 tok/s0.5 sPDF: Llama xLAM 2 8B Fc R on RTX 5070 report
RTX 4060 Ti 16 GB8-bit48K25 tok/s0.7 sPDF: Llama xLAM 2 8B Fc R on RTX 4060 Ti 16 GB report
RTX 5060 Ti 16 GB8-bit48K38 tok/s0.7 sPDF: Llama xLAM 2 8B Fc R on RTX 5060 Ti 16 GB report
Arc A770 16 GB8-bit48K33 tok/s0.8 sPDF: Llama xLAM 2 8B Fc R on Arc A770 16 GB report
Radeon RX 9070 XT8-bit48K45 tok/s0.4 sPDF: Llama xLAM 2 8B Fc R on Radeon RX 9070 XT report
RTX 4070 Ti Super8-bit48K56 tok/s0.4 sPDF: Llama xLAM 2 8B Fc R on RTX 4070 Ti Super report
RTX 4080 Super8-bit48K61 tok/s0.3 sPDF: Llama xLAM 2 8B Fc R on RTX 4080 Super report
RTX 5070 Ti8-bit48K73 tok/s0.4 sPDF: Llama xLAM 2 8B Fc R on RTX 5070 Ti report
RTX 50808-bit48K78 tok/s0.3 sPDF: Llama xLAM 2 8B Fc R on RTX 5080 report
Radeon RX 7900 XTX8-bit112K65 tok/s0.7 sPDF: Llama xLAM 2 8B Fc R on Radeon RX 7900 XTX report
RTX 30908-bit112K76 tok/s0.4 sPDF: Llama xLAM 2 8B Fc R on RTX 3090 report
RTX 40908-bit112K82 tok/s0.2 sPDF: Llama xLAM 2 8B Fc R on RTX 4090 report
Radeon AI PRO R97008-bit128K45 tok/s0.4 sPDF: Llama xLAM 2 8B Fc R on Radeon AI PRO R9700 report
RTX 50908-bit128K137 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on RTX 5090 report
2× RTX 30908-bit128K76 tok/s0.3 sPDF: Llama xLAM 2 8B Fc R on 2× RTX 3090 report
2× RTX 40908-bit128K82 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on 2× RTX 4090 report
RTX PRO 5000 Blackwell 48 GB8-bit128K106 tok/s0.2 sPDF: Llama xLAM 2 8B Fc R on RTX PRO 5000 Blackwell 48 GB report
RTX 6000 Ada8-bit128K78 tok/s0.2 sPDF: Llama xLAM 2 8B Fc R on RTX 6000 Ada report
L40S8-bit128K71 tok/s0.3 sPDF: Llama xLAM 2 8B Fc R on L40S report
2× RTX 50908-bit128K137 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on 2× RTX 5090 report
4× RTX 30908-bit128K76 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on 4× RTX 3090 report
RTX PRO 6000 Blackwell8-bit128K137 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on RTX PRO 6000 Blackwell report
Mac mini M4 16 GB6-bit24K15 tok/s9.9 sPDF: Llama xLAM 2 8B Fc R on Mac mini M4 16 GB report
Mac mini M4 24 GB8-bit52K12 tok/s9.9 sPDF: Llama xLAM 2 8B Fc R on Mac mini M4 24 GB report
Mac mini M4 32 GB8-bit88K12 tok/s9.9 sPDF: Llama xLAM 2 8B Fc R on Mac mini M4 32 GB report
Mac mini M4 Pro 24 GB8-bit52K26 tok/s5.0 sPDF: Llama xLAM 2 8B Fc R on Mac mini M4 Pro 24 GB report
Mac mini M4 Pro 48 GB8-bit128K26 tok/s5.0 sPDF: Llama xLAM 2 8B Fc R on Mac mini M4 Pro 48 GB report
Mac mini M4 Pro 64 GB8-bit128K26 tok/s5.0 sPDF: Llama xLAM 2 8B Fc R on Mac mini M4 Pro 64 GB report
M4 Max 128 GB8-bit128K45 tok/s2.5 sPDF: Llama xLAM 2 8B Fc R on M4 Max 128 GB report
M5 Max 128 GB8-bit128K50 tok/s0.7 sPDF: Llama xLAM 2 8B Fc R on M5 Max 128 GB report
M3 Ultra 96 GB8-bit128K57 tok/s1.4 sPDF: Llama xLAM 2 8B Fc R on M3 Ultra 96 GB report
M3 Ultra 256 GB8-bit128K57 tok/s1.4 sPDF: Llama xLAM 2 8B Fc R on M3 Ultra 256 GB report
M3 Ultra 512 GB8-bit128K57 tok/s1.4 sPDF: Llama xLAM 2 8B Fc R on M3 Ultra 512 GB report
M5 Ultra 512 GB8-bit128K78 tok/s0.4 sPDF: Llama xLAM 2 8B Fc R on M5 Ultra 512 GB report
Ryzen AI Max+ 395 64 GB8-bit128K19 tok/s1.4 sPDF: Llama xLAM 2 8B Fc R on Ryzen AI Max+ 395 64 GB report
Ryzen AI Max+ 395 128 GB8-bit128K19 tok/s1.4 sPDF: Llama xLAM 2 8B Fc R on Ryzen AI Max+ 395 128 GB report
RTX Spark8-bit128K26 tok/s0.5 sPDF: Llama xLAM 2 8B Fc R on RTX Spark report
DGX Spark8-bit128K23 tok/s0.5 sPDF: Llama xLAM 2 8B Fc R on DGX Spark report
Dual DGX Spark8-bit128K23 tok/s0.3 sPDF: Llama xLAM 2 8B Fc R on Dual DGX Spark report
DGX Station GB3008-bit128K390 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on DGX Station GB300 report
2× RTX PRO 6000 Blackwell8-bit128K137 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on 2× RTX PRO 6000 Blackwell report
4× RTX PRO 6000 Blackwell8-bit128K137 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on 4× RTX PRO 6000 Blackwell report
8× RTX PRO 6000 Blackwell8-bit128K137 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on 8× RTX PRO 6000 Blackwell report
A100 80 GB SXM8-bit128K153 tok/s0.3 sPDF: Llama xLAM 2 8B Fc R on A100 80 GB SXM report
H100 SXM8-bit128K229 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on H100 SXM report
4× H200 NVL8-bit128K300 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R on 4× H200 NVL report
8× H200 NVL8-bit128K300 tok/s0.1 sPDF: Llama xLAM 2 8B Fc R 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 DevQuasar-13/Salesforce.Llama-xLAM-2-8b-fc-r-GGUF
vLLM
vllm serve Salesforce/Llama-xLAM-2-8b-fc-r

Questions

How much VRAM does Llama xLAM 2 8B Fc R need?

Llama xLAM 2 8B Fc R needs 4.5 GB for its weights at 4-bit, 6.4 GB with an 8K context and 9.4 GB with 32K. At 8-bit, 9.8 GB.

What is the minimum VRAM for Llama xLAM 2 8B Fc R?

About 5.5 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 Llama xLAM 2 8B Fc R?

8B parameters: 15.0 GB of weights at 16-bit, 4.5 GB at 4-bit.

Can Llama xLAM 2 8B Fc R run on an RTX 4090?

Yes. At 8-bit it holds 112K of context and writes about 82 tokens a second.

More models