Qwen2.5-7B-Instruct-AWQ vs LFM2.5-2.6B-GGUF

Specs, VRAM requirements and download trends — updated 28 September 2026.

Qwen · A · Open weights

Qwen2.5-7B-Instruct-AWQ

Params

7.6 B

Context

32,768

30d

1.6 M

apache-2.0 · commercial OK

LiquidAI · B · Open weights

LFM2.5-2.6B-GGUF

Params

2.6 B

Context

131,072

30d

187 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen2.5-7B-Instruct-AWQ	LFM2.5-2.6B-GGUF
Parameters	7.6 B	2.6 B
Architecture	Qwen2ForCausalLM	—
Context length	32,768	131,072
Licence	apache-2.0	other
Commercial use	Allowed	Unknown
Languages	1	16
Downloads 30d	1,642,251	186,819
Downloads all time	26.1 M	2.5 M
Quantizations on the Hub	SAFETENSORS	GGUF, SAFETENSORS
Gated	No	No
First seen on the Hub	2024-09-17	2026-08-01

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

4.7 M187 K

Qwen2.5-7B-Instruct-AWQ LFM2.5-2.6B-GGUF

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

LFM2.5-2.6B-GGUF · Q4_0 2.6 GB / 24 GB

✅ Runs comfortably

Qwen2.5-7B-Instruct-AWQ · fp16 7.8 GB / 24 GB

✅ Runs comfortably

LFM2.5-2.6B-GGUF · fp16 @ 128K ctx 18.6 GB / 24 GB

✅ Runs comfortably

Adjacent comparisons

Qwen2.5-7B-Instruct-AWQ vs Qwen3-14B

Qwen3-8B vs Qwen2.5-7B-Instruct-AWQ

Qwen2.5-7B-Instruct vs Qwen2.5-7B-Instruct-AWQ

Llama-3.1-8B-Instruct vs Qwen2.5-7B-Instruct-AWQ

Qwen3-4B vs Qwen2.5-7B-Instruct-AWQ

gpt-oss-20b vs Qwen2.5-7B-Instruct-AWQ