SmolLM-1.7B-Instruct-quantized.w4a16 vs Qwen2.5-Math-1.5B
Specs, VRAM requirements and download trends — updated 16 August 2026.
nm-testing · A
Params
1.8 B
Context
2,048
30d
571 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | SmolLM-1.7B-Instruct-quantized.w4a16 | Qwen2.5-Math-1.5B |
|---|---|---|
| Parameters | 1.8 B | 1.5 B |
| Architecture | LlamaForCausalLM | Qwen2ForCausalLM |
| Context length | 2,048 | 4,096 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 571,201 | 207,749 |
| Downloads all time | 5.5 M | 7.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-08-23 | 2024-09-16 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
1.5 M208 K
SmolLM-1.7B-Instruct-quantized.w4a16
Qwen2.5-Math-1.5B
A overtook B on 3 Sep
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
SmolLM-1.7B-Instruct-quantized.w4a16 · fp16
2.7 GB / 24 GB
Qwen2.5-Math-1.5B · fp16
4.1 GB / 24 GB
Adjacent comparisons
Qwen3-0.6B vs SmolLM-1.7B-Instruct-quantized.w4a16
Qwen2.5-1.5B-Instruct vs SmolLM-1.7B-Instruct-quantized.w4a16
Llama-3.2-1B-Instruct vs SmolLM-1.7B-Instruct-quantized.w4a16
Qwen3-0.6B vs Qwen2.5-Math-1.5B
Qwen3-1.7B vs SmolLM-1.7B-Instruct-quantized.w4a16
Qwen3-4B vs SmolLM-1.7B-Instruct-quantized.w4a16