Skip to content
Weights Not Walls
Menu

Qwen

Qwen3.5-9B-Base

Reviewedaccepts images
Size
9.7B parameterscounted from the safetensors header on the Hub
Licence
custom, read it, Apache License 2.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
On the Hub since
26 Feb 2026the date the repo was created
Context length
256k tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)Qwen3_5ForConditionalGeneration
On Hugging Face
Qwen/Qwen3.5-9B-Base265k downloads in the last 30 days, 159 likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.25 GB, worked out from the model's config (Qwen/Qwen3.5-9B-Base), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

mradermacher/Qwen3.5-9B-Base-GGUF (converted by mradermacher), 2.9k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file Qwen3.5-9B-Base.mmproj-f16.gguf (0.86 GB), not counted below.

FormatSizeMemory neededGet it
Q2_K3.6 GBfile size4.3 GB3.6 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:Q2_K
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:Q2_K
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.Q2_K.gguf" --local-dir Qwen3.5-9B-Base-GGUF
Q3_K_S4.0 GBfile size4.7 GB4.0 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:Q3_K_S
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:Q3_K_S
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.Q3_K_S.gguf" --local-dir Qwen3.5-9B-Base-GGUF
Q3_K_M4.3 GBfile size5.1 GB4.3 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:Q3_K_M
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:Q3_K_M
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.Q3_K_M.gguf" --local-dir Qwen3.5-9B-Base-GGUF
Q3_K_L4.6 GBfile size5.3 GB4.6 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:Q3_K_L
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:Q3_K_L
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.Q3_K_L.gguf" --local-dir Qwen3.5-9B-Base-GGUF
IQ4_XS4.9 GBfile size5.6 GB4.9 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:IQ4_XS
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:IQ4_XS
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.IQ4_XS.gguf" --local-dir Qwen3.5-9B-Base-GGUF
Q4_K_S5.0 GBfile size5.7 GB5.0 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:Q4_K_S
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:Q4_K_S
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.Q4_K_S.gguf" --local-dir Qwen3.5-9B-Base-GGUF
Q4_K_M5.2 GBfile size6.0 GB5.2 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:Q4_K_M
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:Q4_K_M
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.Q4_K_M.gguf" --local-dir Qwen3.5-9B-Base-GGUF
Q5_K_S5.9 GBfile size6.6 GB5.9 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:Q5_K_S
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:Q5_K_S
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.Q5_K_S.gguf" --local-dir Qwen3.5-9B-Base-GGUF
Q5_K_M6.0 GBfile size6.8 GB6.0 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:Q5_K_M
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:Q5_K_M
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.Q5_K_M.gguf" --local-dir Qwen3.5-9B-Base-GGUF
Q6_K6.9 GBfile size7.6 GB6.9 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:Q6_K
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:Q6_K
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.Q6_K.gguf" --local-dir Qwen3.5-9B-Base-GGUF
Q8_08.9 GBfile size9.6 GB8.9 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:Q8_0
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:Q8_0
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.Q8_0.gguf" --local-dir Qwen3.5-9B-Base-GGUF
F1616.7 GBfile size17.4 GB16.7 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/Qwen3.5-9B-Base-GGUF:F16
Ollama
ollama run hf.co/mradermacher/Qwen3.5-9B-Base-GGUF:F16
Download
hf download mradermacher/Qwen3.5-9B-Base-GGUF --include "Qwen3.5-9B-Base.f16.gguf" --local-dir Qwen3.5-9B-Base-GGUF

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights18.0 GBfile size18.7 GB18.0 + 0.25 + 0.50
hf download Qwen/Qwen3.5-9B-Base --local-dir Qwen3.5-9B-Base
Other conversions (6; sizes not read)

The Hub tags 53 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.