QW

LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2

QwenGGUF by mradermacherUpdated 2026-05-30
Download on Hugging Face
Parameters8.34B
Context125K
Layers24
Architecturelfm2moe
Smallest quant3.1 GB
Quick answer

LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 needs about 7.2 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 3.1 GB (Q2_K) to 16.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 – a 8.34B parameter MOE instruct model

LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 is a 8.34B parameter mixture of experts model with 1 active expert. It supports 128k context tokens and is trained on a custom DISTILL dataset using Qwen 3.6 35B-A3B as a teacher.

Good at

  • Tool usage
  • Instruct style responses
  • Large context handling

Limits

  • No vision support
  • Requires 8k+ context window
  • Apache-2.0 license

Best for

  • Chatbot instruction handling
  • Long-form content generation
  • Tool integration scripts

Who it’s for. Developers building instruction‑driven chatbots or content generators who need a large context window and tool‑use capability. The model is suitable for local deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 5.2 GB
Fits Get file →
Q3_K_S3.6 GB 5.8 GB
Fits Get file →
Q3_K_M4.0 GB 6.1 GB
Fits Get file →
Q3_K_L4.3 GB 6.4 GB
Fits Get file →
IQ4_XS4.5 GB 6.6 GB
Fits Get file →
Q4_K_S4.8 GB 6.9 GB
Fits Get file →
Q4_K_M5.0 GB 7.2 GB
Fits Get file →
Q5_K_S5.8 GB 7.9 GB
Tight Get file →
Q5_K_M5.9 GB 8.0 GB
Too big Get file →
Q6_K6.8 GB 9.0 GB
Too big Get file →
Q8_08.9 GB 11.0 GB
Too big Get file →
F1616.7 GB 18.8 GB
Too big Get file →

For 8GB VRAM, use Q2_K (3.08 GB, ~5.2 GB RAM at 8k context). For 16GB VRAM, Q4_K_M (5.04 GB, ~7.2 GB RAM) or Q5_K_M (5.92 GB, ~8 GB RAM). For 24GB VRAM, Q6_K (6.85 GB, ~9 GB RAM) or Q8_0 (8.87 GB, ~11 GB RAM).

What GPU do you need for LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_S (3.6 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 11.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.7 GB file, about 18.8 GB in use).

Which LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 quant should you choose?

Q4_K_M is the usual starting point for LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2: it balances file size and quality well. Here it is a 5.0 GB file.

The Q8_0 file is 8.9 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 3.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2moe
Parameters8.34B (approximate, mixture of experts)
Active parameters1B
Layers24
Trained context128,000 tokens
KV cache (fp16)192 KB per token

Frequently asked questions about LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2

How much VRAM does LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 GGUF?

It depends on the quant: Q2_K is 3.1 GB, Q3_K_S is 3.6 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, IQ4_XS is 4.5 GB, Q4_K_S is 4.8 GB and 6 more.

What context length does LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 GGUF?

The files are on Hugging Face in the mradermacher/LFM2-8B-A1B-Instruct-Quantum-IQ1C-Qwen3.6-35B-A3B-DISTILL2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8GB VRAM?

Yes, the Q2_K quant is 3.08 GB and requires about 5.2 GB RAM at 8k context, fitting within 8GB VRAM.

What is the minimum context window I should use?

The model recommends a minimum of 8k context; it supports up to 128k tokens.

Does this model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of LFM2-8B-A1B-Instruct-Quantum-IQ1C-Qwen3.6-35B-A3B-DISTILL2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other small models

All small models →