SmolLM-1.7B-Instruct-quantized.w4a16 vs Kimi-K3-DSpark

Specs, VRAM requirements and download trends — updated 21 September 2026.

nm-testing · A
Params
1.8 B
Context
2,048
30d
571 K
apache-2.0 · commercial OK
RadixArk · B
Params
2.3 B
Context
1,048,576
30d
3.7 M

Specification comparison

Differences are highlighted; identical values are muted.

Specification SmolLM-1.7B-Instruct-quantized.w4a16 Kimi-K3-DSpark
Parameters 1.8 B 2.3 B
Architecture LlamaForCausalLM DSparkDraftModel
Context length 2,048 1,048,576
Licence apache-2.0
Commercial use Allowed Unknown
Languages 1
Downloads 30d 571,201 3,658,082
Downloads all time 5.5 M 6.5 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-08-23 2026-07-27

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

3.7 M168 K
SmolLM-1.7B-Instruct-quantized.w4a16 Kimi-K3-DSpark

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
✅ Runs comfortably
Kimi-K3-DSpark · fp16 @ 1024K ctx 48.6 GB / 24 GB
❌ Won’t fit

Adjacent comparisons