LFM2.5 350M — Hardware Requirements & GPU Compatibility
Chat
LFM2.5 350M is a 354M-parameter open language model from Liquid AI in the LFM2.5 family. It supports a context window of up to 128,000 tokens. At Q4_K_M it needs about 0.58 GB of VRAM — see which GPUs and Macs can run it below.
91.1K downloads
377 likesSpecifications
- Publisher
- Liquid AI
- Family
- LFM2.5
- Parameters
- 354M
- Architecture
- Lfm2ForCausalLM
- Context Length
- 128,000 tokens
- Vocabulary Size
- 65,536
- Release Date
- 2026-03-31
- License
- Other
Get Started
HuggingFace
How Much VRAM Does LFM2.5 350M Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q3_K_S | 3.50 | 0.5 GB | 4.7 GB | 0.16 GB | 3-bit small quantization |
| Q2_K | 3.40 | 0.5 GB | 4.6 GB | 0.15 GB | 2-bit quantization with K-quant improvements |
| Q4_0 | 4.00 | 0.5 GB | 4.7 GB | 0.18 GB | 4-bit legacy quantization |
| Q3_K_M | 3.90 | 0.5 GB | 4.7 GB | 0.17 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 0.6 GB | 4.7 GB | 0.21 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 0.6 GB | 4.8 GB | 0.25 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 0.7 GB | 4.8 GB | 0.29 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 0.7 GB | 4.8 GB | 0.35 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run LFM2.5 350M?
Q4_K_M · 0.6 GBLFM2.5 350M (Q4_K_M) requires 0.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 128K context window can add up to 4.1 GB, bringing total usage to 4.7 GB. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run LFM2.5 350M?
Q4_K_M · 0.6 GB59 devices with unified memory can run LFM2.5 350M, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download LFM2.5 350M
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does LFM2.5 350M need?
LFM2.5 350M requires 0.6 GB of VRAM at Q4_K_M, or 1.1 GB at BF16. Full 128K context adds up to 4.1 GB (4.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 354M × 4.8 bits ÷ 8 = 0.2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4.5 GB (at full 128K context)
VRAM usage by quantization
Q4_K_M0.6 GBQ4_K_M + full context4.7 GB- What's the best quantization for LFM2.5 350M?
For LFM2.5 350M, Q4_K_M (0.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (0.6 GB) provides better quality if you have the VRAM. The smallest option is Q3_K_S at 0.5 GB.
VRAM requirement by quantization
Q3_K_S0.5 GBQ3_K_M0.5 GBQ4_K_S0.6 GBQ4_K_M ★0.6 GBQ5_K_M0.6 GBBF161.1 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run LFM2.5 350M on a Mac?
LFM2.5 350M requires at least 0.5 GB at Q3_K_S, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run LFM2.5 350M locally?
Yes — LFM2.5 350M can run locally on consumer hardware. At Q4_K_M quantization it needs 0.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is LFM2.5 350M?
At Q4_K_M, LFM2.5 350M can reach ~7586 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1130 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 0.6 × 0.65 = ~8966 tok/s
Estimated speed at Q4_K_M (0.6 GB)
~8966 tok/s~1130 tok/s~8966 tok/s~7586 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of LFM2.5 350M?
At Q4_K_M, the download is about 0.21 GB. The full-precision BF16 version is 0.71 GB. The smallest option (Q3_K_S) is 0.16 GB.
- Which GPUs can run LFM2.5 350M?
50 consumer GPUs can run LFM2.5 350M at Q4_K_M (0.6 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 50 GPUs have plenty of headroom for comfortable inference.
- Which devices can run LFM2.5 350M?
59 devices with unified memory can run LFM2.5 350M at Q4_K_M (0.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.