The LPDDR5 memory is listed with a 16GB maximum; no RAM upgrade is assumed.
Listing evidence: 2026-09-25. Amazon.com base price visible in an owner-supplied screenshot reviewed 25 Sep 2026; capture time not supplied. Dated reference, not a live quote. Excludes card signup offers, coupons, tax and shipping.
Fixed 24GB memory and internal storage limit model size; no CUDA support; Amazon main-offer price and stock were not verified in this run.
Listing evidence: 2026-10-03. Apple US launch price announced 22 September 2026: USD 1,699. Dated manufacturer reference, not an Amazon offer; tax and shipping may differ.
Memory is soldered and shared with the operating system.
Listing evidence: 2026-09-24. GMKtec, EVO-X2 / 64GB / 1TB, recorded 22 Sep 2026; exact ASIN capacity identified 24 Sep. This is a dated reference, not a current Amazon price; tax, shipping and bundle contents may differ.
Weight size is not tested compatibility or speed. Check runtime support and memory for context before buying. Prices are dated references. As an Amazon Associate I earn from qualifying purchases.
How these options are selected
Up to three platforms, with the lowest dated reference price on each. Unknown prices follow known prices. Each memory pool keeps a reserve: 30% (minimum 2 GB) for system or unified memory; 20% (minimum 1 GB) for dedicated VRAM. System RAM is for CPU inference. This check does not establish GPU allocation, software support or context capacity.
Model file and details
Provider
Liquid AI
Total parameters
1,728,801,536
Exact file size
1,099,627,808 bytes
Quantization / precision
Q4_K_M
Weight repository
LiquidAI/LFM3-1.7B-GGUF
Original model repository
LiquidAI/LFM3-1.7B
Weight revision
bad5729bba61d076fff20d2548e62526665af215
Model revision
ac2586a34f1a1c03329dbdcdefabd8b6478ddaa7
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-27
Date evidence
Liquid AI LFM3 family announcement dated 27 October 2026; official source and GGUF model cards reviewed on 28 October. Exact source parameter count includes modality encoders; the language GGUF metadata count excludes separate encoders. Pretrained Base checkpoint is a separate fine-tuning starting point, not this chat model.
These scores were compiled from the linked sources. These published scores were not independently tested here. Different prompts, precision, thinking budgets and tools can change results.
GPQA Diamond
63.37 / 100
Hard science questions. This is a science reasoning test, not an overall intelligence score.
Benchmark efficiency: 57.629 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.
Test settings: Liquid AI BF16 source evaluation with vLLM at 262,144-token context. Temperature 0.6, top_p 0.95; no output cap beyond full context. IFEval strictness and exact harness revisions are not stated.
Publisher source-checkpoint result, not an independent evaluation or a measurement of the selected quantized file. No repeated-run confidence interval is supplied. File size covers language weights only; it is not runtime RAM. Allow additional memory for context, runtime and media. LFM Open License v1.0 applies; commercial use at or above the defined USD 10 million annual-revenue threshold needs a separate license. Text chat, tools and local agents; 262,144-token source limit. Not recommended by the publisher for complex agentic coding or multi-step reasoning. Requires llama.cpp b11960/v0.8.0 or newer, or an app engine with LFM3 support. Q4_K_M is not the separately trained QAD Q4_0 artifact.
Solving coding problems. Version 6 only; published pass rates can vary with generation settings.
Benchmark efficiency: 66.804 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.
Test settings: Liquid AI BF16 source evaluation with vLLM at 262,144-token context. Temperature 0.6, top_p 0.95; no output cap beyond full context. IFEval strictness and exact harness revisions are not stated.
Publisher source-checkpoint result, not an independent evaluation or a measurement of the selected quantized file. No repeated-run confidence interval is supplied. File size covers language weights only; it is not runtime RAM. Allow additional memory for context, runtime and media. LFM Open License v1.0 applies; commercial use at or above the defined USD 10 million annual-revenue threshold needs a separate license. Text chat, tools and local agents; 262,144-token source limit. Not recommended by the publisher for complex agentic coding or multi-step reasoning. Requires llama.cpp b11960/v0.8.0 or newer, or an app engine with LFM3 support. Q4_K_M is not the separately trained QAD Q4_0 artifact.
Following precise instructions. These cards report IFEval without consistently specifying prompt-level versus instruction-level scoring. Treat this view as approximate.
Benchmark efficiency: 87.902 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.
Test settings: Liquid AI BF16 source evaluation with vLLM at 262,144-token context. Temperature 0.6, top_p 0.95; no output cap beyond full context. IFEval strictness and exact harness revisions are not stated.
Publisher source-checkpoint result, not an independent evaluation or a measurement of the selected quantized file. No repeated-run confidence interval is supplied. File size covers language weights only; it is not runtime RAM. Allow additional memory for context, runtime and media. LFM Open License v1.0 applies; commercial use at or above the defined USD 10 million annual-revenue threshold needs a separate license. Text chat, tools and local agents; 262,144-token source limit. Not recommended by the publisher for complex agentic coding or multi-step reasoning. Requires llama.cpp b11960/v0.8.0 or newer, or an app engine with LFM3 support. Q4_K_M is not the separately trained QAD Q4_0 artifact.
Choosing and calling functions. Published BFCL v4 scores; tool environments and settings differ.
Benchmark efficiency: 64.922 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.
Test settings: Liquid AI BF16 source evaluation with vLLM at 262,144-token context. BFCL V4 uses greedy decoding and up to 32,768 output tokens.
Publisher source-checkpoint result, not an independent evaluation or a measurement of the selected quantized file. No repeated-run confidence interval is supplied. File size covers language weights only; it is not runtime RAM. Allow additional memory for context, runtime and media. LFM Open License v1.0 applies; commercial use at or above the defined USD 10 million annual-revenue threshold needs a separate license. Text chat, tools and local agents; 262,144-token source limit. Not recommended by the publisher for complex agentic coding or multi-step reasoning. Requires llama.cpp b11960/v0.8.0 or newer, or an app engine with LFM3 support. Q4_K_M is not the separately trained QAD Q4_0 artifact.
Context and version evidence: The repository and file name identify the selected model. Revision hashes are shown above when recorded. Tested context length, full hardware configuration and run date are not consistently recorded in this snapshot. Only settings explicitly stated in each benchmark record are known.
The 1.1 GB figure covers model weights in this file. It excludes the context cache, runtime, operating system and any separate multimodal files. It is not a measured RAM requirement or a token-generation speed.
Confirm model architecture and quantization support in your runner. The selected weights use 1.1 GB; this excludes context cache, runtime buffers and other programs.
These are the first listed tiers that pass our reserve policy, not measured minimum requirements. System RAM and VRAM remain separate. Use the memory tool to change the reserve for your context and runner.