Qwen
Qwen3.5 9B Base
Qwen3.5 9B Base is an open-weights 9B-parameter model by Qwen. It holds an Intelligence score of 59.3 on the local.ai leaderboard (2026-08 snapshot).
open weights
59.3
local.ai Intelligence
Parameters
9B
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2026-04-23
Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.
Does it fit your hardware?
Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.
Q4_K_M 5.2GQ6_K 8.1GQ8_0 9.9GFP16 18G| Quantization | ≈ File size | Note |
|---|---|---|
| IQ2_XXS | 2.4 GB | Extreme compression, largest quality loss |
| IQ3_XXS | 3.2 GB | Very small |
| Q3_K_M | 4.1 GB | Small |
| NVFP4 | 4.5 GB | NVIDIA 4-bit |
| Q4_K_S | 4.9 GB | Common |
| Q4_K_M | 5.2 GB | Most common sweet spot |
| Q5_K_M | 6.8 GB | Balanced |
| Q6_K | 8.1 GB | Near-lossless |
| Q8_0 | 9.9 GB | Near-lossless |
| FP16 | 18 GB | Original weights |
Actual files on HuggingFace
| File | Size |
|---|---|
| model.safetensors-00003-of-00004.safetensors | 5.00 GB |
| model.safetensors-00002-of-00004.safetensors | 4.97 GB |
| model.safetensors-00001-of-00004.safetensors | 4.91 GB |
| model.safetensors-00004-of-00004.safetensors | 3.10 GB |
GGUF: mradermacher/Qwen3.5-9B-Base-i1-GGUF · 737 downloads
| File | Size | |
|---|---|---|
| Qwen3.5-9B-Base.i1-IQ1_M.gguf | 2.68 GB | download |
| Qwen3.5-9B-Base.i1-IQ1_S.gguf | 2.55 GB | download |
| Qwen3.5-9B-Base.i1-IQ2_M.gguf | 3.36 GB | download |
| Qwen3.5-9B-Base.i1-IQ2_S.gguf | 3.19 GB | download |
| Qwen3.5-9B-Base.i1-IQ2_XS.gguf | 3.06 GB | download |
| Qwen3.5-9B-Base.i1-IQ2_XXS.gguf | 2.89 GB | download |
| Qwen3.5-9B-Base.i1-IQ3_M.gguf | 4.11 GB | download |
| Qwen3.5-9B-Base.i1-IQ3_S.gguf | 4.07 GB | download |
| Qwen3.5-9B-Base.i1-IQ3_XS.gguf | 3.95 GB | download |
| Qwen3.5-9B-Base.i1-IQ3_XXS.gguf | 3.67 GB | download |
| Qwen3.5-9B-Base.i1-IQ4_NL.gguf | 5.05 GB | download |
| Qwen3.5-9B-Base.i1-IQ4_XS.gguf | 4.84 GB | download |
GGUF: mradermacher/Qwen3.5-9B-Base-GGUF · 398 downloads
| File | Size | |
|---|---|---|
| Qwen3.5-9B-Base.IQ4_XS.gguf | 4.87 GB | download |
| Qwen3.5-9B-Base.Q2_K.gguf | 3.56 GB | download |
| Qwen3.5-9B-Base.Q3_K_L.gguf | 4.59 GB | download |
| Qwen3.5-9B-Base.Q3_K_M.gguf | 4.31 GB | download |
| Qwen3.5-9B-Base.Q3_K_S.gguf | 3.97 GB | download |
| Qwen3.5-9B-Base.Q4_K_M.gguf | 5.24 GB | download |
| Qwen3.5-9B-Base.Q4_K_S.gguf | 4.98 GB | download |
| Qwen3.5-9B-Base.Q5_K_M.gguf | 6.02 GB | download |
| Qwen3.5-9B-Base.Q5_K_S.gguf | 5.87 GB | download |
| Qwen3.5-9B-Base.Q6_K.gguf | 6.85 GB | download |
| Qwen3.5-9B-Base.Q8_0.gguf | 8.87 GB | download |
| Qwen3.5-9B-Base.f16.gguf | 16.69 GB | download |
What you save self-hosting this model
Uses the model's own API price when it exists; otherwise the closest commercial equivalent.
Waiting for hardware detection…
RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.