willitrun·ai

Can LFM2.5 8B A1B run on GTX 1080 8GB?

YES — Tight Fit

A78Great
Estimated from fit model

LFM2.5 8B A1B needs ~7.1 GB VRAM. GTX 1080 8GB has 8.0 GB. With Q4_K_M quantization, expect ~89 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: LowStack: StandardBottleneck: Balanced
Share:

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 7.1 GB, 88.7 tok/s, Tight fit
7.1 GB required8.0 GB available
89% VRAM used

Fit status

Tight fit

Decode

88.7 tok/s

TTFT

2182 ms

Safe context

97K

Memory

7.1 GB / 8.0 GB

Memory breakdown

Weights5.2 GB
KV Cache0.2 GB
Runtime0.9 GB
Headroom0.8 GB

See how fast it feels

See how fast it feelsLFM2.5 8B A1B on GTX 1080 8GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API. When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed. Key benefits of running locally: - Full privacy: your prompts never leave your machine - No per-token cost or rate limits - Works offline once the model is downloaded - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb: Model size Q4 (4-bit) Q8 (8-bit) FP16 7B params ~4.3 GB ~7.5 GB ~14 GB 13B params ~7.9 GB ~13.9 GB ~26 GB 70B params ~42.7 GB ~74.9 GB ~140 GB Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 88.7 tok/s decode · 2.2s TTFT (warm) · 222 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Older PCIe generation

PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.

Best improvement path

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatATight fit88.7 tok/s1190 ms89K
CodingATight fit88.7 tok/s2182 ms97K
Agentic CodingATight fit88.7 tok/s3174 ms97K
ReasoningATight fit88.7 tok/s2579 ms97K
RAGATight fit88.7 tok/s3967 ms97K

Inference speed

LFM2.5 8B A1B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for LFM2.5 8B A1B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~508 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / MacMemoryQuantSpeed (tok/s)Fits?
NVIDIARTX 5090 32GB
32 GBQ4_K_M507.8Fits
RX 7900 XTX 24GB
24 GBQ4_K_M324.8Fits
NVIDIARTX 4090 24GB
24 GBQ4_K_M324.0Fits
NVIDIARTX 3090 24GB
24 GBQ4_K_M277.1Fits
Mac Studio M3 Ultra 256GB
256 GBQ4_K_M261.7Fits
NVIDIARTX 4080 Super 16GB
16 GBQ4_K_M258.4Fits
Mac Studio M2 Ultra 128GB
128 GBQ4_K_M218.1Fits
Mac Studio M1 Ultra 128GB
128 GBQ4_K_M206.8Fits
MacBook Pro M4 Max 128GB
128 GBQ4_K_M161.7Fits
MacBook Pro M4 Max 64GB
64 GBQ4_K_M161.7Fits
NVIDIARTX 4070 12GB
12 GBQ4_K_M159.9Fits
MacBook Pro M3 Max 64GB
64 GBQ4_K_M112.8Fits
MacBook Pro M1 Max 64GB
64 GBQ4_K_M103.4Fits
NVIDIARTX 3060 12GB
12 GBQ4_K_M100.5Fits
MacBook Pro M4 Pro 48GB
48 GBQ4_K_M98.8Fits
NVIDIARTX 4060 8GB
8 GBQ4_K_M84.0Tight

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How LFM2.5 8B A1B (8.5B params) fits at each quantization level on GTX 1080 8GB (8.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
3.3 GB
LowA78
Q3_K_S
3
4.2 GB
LowA77
NVFP4
4
4.8 GB
MediumA77
Q4_K_MBest for your GPU
4
5.2 GB
MediumA77
Q5_K_M
5
6.1 GB
HighF0
Q6_K
6
7.0 GB
HighF0
Q8_0
8
9.1 GB
Very HighF0
F16
16
17.4 GB
MaximumF0

Get started

Copy-paste commands to run LFM2.5 8B A1B on your machine.

Run

lms load LFM2.5-8B-A1B && lms server start

Your hardware

More models your GTX 1080 8GB can run

ModelParamsGradeDecodeCapabilities
AlibabaQwen 3.5 9B9BA19 tok/s
Tsinghua/ZhipuCodeGeeX 4 9B9BA37.6 tok/s

Frequently asked questions

Can GTX 1080 8GB run LFM2.5 8B A1B?

Yes, GTX 1080 8GB can run LFM2.5 8B A1B with a A grade (Tight fit). Expected decode speed: 88.7 tok/s.

How much VRAM does LFM2.5 8B A1B need?

LFM2.5 8B A1B (8.5B parameters) requires approximately 7.1 GB of memory with Q4_K_M quantization.

What is the best quantization for LFM2.5 8B A1B?

The recommended quantization for LFM2.5 8B A1B is Q4_K_M, which balances quality and memory efficiency.

What speed will LFM2.5 8B A1B run at on GTX 1080 8GB?

On GTX 1080 8GB, LFM2.5 8B A1B achieves approximately 88.7 tokens per second decode speed with a time-to-first-token of 2182ms using Q4_K_M quantization.

Can GTX 1080 8GB run LFM2.5 8B A1B for coding?

For coding workloads, LFM2.5 8B A1B on GTX 1080 8GB receives a A grade with 88.7 tok/s and 97K context.

What context window can LFM2.5 8B A1B use on GTX 1080 8GB?

On GTX 1080 8GB, LFM2.5 8B A1B can safely use up to 97K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.

See all results for GTX 1080 8GBSee all hardware for LFM2.5 8B A1B
Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/lfm2.5-8b-a1b-on-gtx-1080-8gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: