LFM2.5-1.2B-Instruct
LiquidAIothertext

LFM2.5-1.2B-Instruct

Updated Jun 7, 2026
Parameters
1.2B
Context
128,000
License
other
Updated
Jun 7, 2026

Intelligence benchmarks

Artificial Analysis indexes - compared with the best open and proprietary models

Intelligence

8.0

AA Index

Coding

0.8

AA Index

Agentic

3.6

AA Index

Intelligence Index - LFM2.5-1.2B-Instruct vs. the field

Best open-weight models (you can run locally) and leading proprietary models for context.

Claude Opus 4.8 (max)
61.4
closed
GPT-5.5 (xhigh)
60.2
closed
Claude Opus 4.7 (max)
57.3
closed
Gemini 3.1 Pro Preview
57.2
closed
Qwen3.7 Max
56.6
closed
Kimi K2.6
53.9
open
MiMo-V2.5-Pro
53.8
open
LFM2.5-1.2B-Instruct
8
open

Coding Index comparison

GPT-5.5 (xhigh)
59.1
closed
Claude Opus 4.8 (max)
56.7
closed
Gemini 3.1 Pro Preview
55.5
closed
Claude Opus 4.7 (Non-reasoning, high)
53.1
closed
GPT-5.3 Codex (xhigh)
53.1
closed
DeepSeek V4 Pro (Max)
47.5
open
Kimi K2.6
47.1
open
LFM2.5-1.2B-Instruct
0.8
open

Agentic Index comparison

Claude Opus 4.8 (max)
77.8
closed
GPT-5.5 (xhigh)
74.1
closed
Claude Opus 4.7 (max)
71.3
closed
Gemini 3.5 Flash (medium)
70.4
closed
MiniMax-M3
68.6
closed
MiMo-V2.5-Pro
67.4
open
DeepSeek V4 Pro (Max)
67.2
open
LFM2.5-1.2B-Instruct
3.6
open

Benchmark data from Artificial Analysis · updated 2026-06-07.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GPQA32.6

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit LFM2.5-1.2B-Instruct with real runtime overhead.
Q4_K_M
1 GB
Q5_K_M
1 GB
Q8_0
1 GB
FP16
2 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve LiquidAI/LFM2.5-1.2B-Instruct

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

LFM2.5-1.2B-Instruct

LFM2.5-1.2B-Instruct is a 1.2B-parameter other model from LiquidAI. It scores 8 on the Artificial Analysis Intelligence Index (coding 0.8). At Q4_K_M it needs roughly 1 GB of VRAM, placing it in the cpu hardware tier.

Specifications

SpecValue
Parameters1.2B
Context length128K tokens
Licenseother
Modalitiestext
Released2026-01-06
WeightsLiquidAI/LFM2.5-1.2B-Instruct

Benchmarks

Artificial Analysis Intelligence Index - LFM2.5-1.2B-Instruct vs. leading closed models:

ModelIntelligenceCodingGPQA
LFM2.5-1.2B-Instruct80.832.6
GPT-5.5 (xhigh)60.259.193.5
Claude Opus 4.8 (max)61.456.792
Gemini 3.1 Pro Preview57.255.594.1
Grok 4.3 (high)53.24190.1

Source: Artificial Analysis (2026-06-04).

VRAM requirements

QuantVRAMRuns on
Q4_K_M~1 GBRTX 4060, RTX 3060 8GB
Q5_K_M~1 GBRTX 4060, RTX 3060 8GB
Q8_0~1 GBRTX 4060, RTX 3060 8GB
FP16~2 GBRTX 4060, RTX 3060 8GB

VRAM is estimated from parameter count; MoE models still need all weights resident.

How to run

vLLM:

vllm serve LiquidAI/LFM2.5-1.2B-Instruct

Popularity

LFM2.5-1.2B-Instruct has 391,492 downloads in the last month on HuggingFace and 600 likes.

Frequently asked

Quick answers to common questions

How much VRAM does LFM2.5-1.2B-Instruct need?

LFM2.5-1.2B-Instruct with 1.2B parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is LFM2.5-1.2B-Instruct better than other LiquidAI models?

LFM2.5-1.2B-Instruct has 1.2B parameters with 128,000 context - a strong choice for general use.

What license is LFM2.5-1.2B-Instruct under?

LFM2.5-1.2B-Instruct is released under the other license, making it suitable for most commercial and personal projects.

What hardware runs LFM2.5-1.2B-Instruct well?

With 1.2B parameters, LFM2.5-1.2B-Instruct requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for LFM2.5-1.2B-Instruct?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can LFM2.5-1.2B-Instruct's context window handle?

LFM2.5-1.2B-Instruct supports a 128,000-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with LFM2.5-1.2B-Instruct?

LFM2.5-1.2B-Instruct competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec

Comments coming soon

Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.