Qwen3-Coder-Next-8bit
This model NexVeridian/Qwen3-Coder-Next-8bit was converted to MLX format from Qwen/Qwen3-Coder-Next using mlx-lm version 0.31.3.
Params
79.7 B
Context
262,144
Downloads 30d
336 K
Likes
3
Download history
daily snapshots · 13 days336 K139 K
Oct 29Nov 2Nov 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | u32 | 84.7 GB | 105.6 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 84.7 GB | 476.1 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-coder-next-8bit
{
"hf_id": "NexVeridian/Qwen3-Coder-Next-8bit",
"params_b": 79.67,
"context_length": 262144,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 336073,
"vram_estimates": [
{ "quant": "u32", "gb": 105.6 }
],
"updated_at": "2026-10-29T01:00:38Z"
}
Specifications
- Architecture
- Qwen3NextForCausalLM
- Parameters
- 79.7 B
- Tensor type
- U32
- Context length
- 262,144
- Vocabulary
- 151,936
- Layers / heads
- 48 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-02-03
- Base model
- Qwen3-Coder-Next
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-29
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model