HN

Need help?
<- Back
Qwen3-Coder-Next

Qwen3-Coder-Next

danielhanchen

Comments (349)

  • simonw
    This GGUF is 48.4GB - https://huggingface.co/Qwen/Qwen3-Coder-Next-GGUF/tree/main/... - which should be usable on higher end laptops.I still haven't experienced a local model that fits on my 64GB MacBook Pro and can run a coding agent like Codex CLI or Claude code well enough to be useful.Maybe this will be the one? This Unsloth guide from a sibling comment suggests it might be: https://unsloth.ai/docs/models/qwen3-coder-next
  • danielhanchen
    For those interested, made some Dynamic Unsloth GGUFs for local deployment at https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF and made a guide on using Claude Code / Codex locally: https://unsloth.ai/docs/models/qwen3-coder-next
  • simonw
    I got this running locally using llama.cpp from Homebrew and the Unsloth quantized model like this: brew upgrade llama.cpp # or brew install if you don't have it yet Then: llama-cli \ -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_XL \ --fit on \ --seed 3407 \ --temp 1.0 \ --top-p 0.95 \ --min-p 0.01 \ --top-k 40 \ --jinja That opened a CLI interface. For a web UI on port 8080 along with an OpenAI chat completions compatible endpoint do this: llama-server \ -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_XL \ --fit on \ --seed 3407 \ --temp 1.0 \ --top-p 0.95 \ --min-p 0.01 \ --top-k 40 \ --jinja It's using about 28GB of RAM.
  • skhameneh
    It’s hard to elaborate just how wild this model might be if it performs as claimed. The claims are this can perform close to Sonnet 4.5 for assisted coding (SWE bench) while using only 3B active parameters. This is obscenely small for the claimed performance.
  • tommyjepsen
    I got the Qwen3 Coder 30B running locally on mac Mac M4 Max 36GB. It was slow, but it worked and did do some decent stuff: https://www.youtube.com/watch?v=7mAPaRbsjTUVideo is speed up. I ran it through LM Studio and then OpenCode. Wrote a bit about how I set it all up here: https://www.tommyjepsen.com/blog/run-llm-locally-for-coding
  • vessenes
    3B active parameters, and slightly worse than GLM 4.7. On benchmarks. That's pretty amazing! With better orchestration tools being deployed, I've been wondering if faster, dumber coding agents paired with wise orchestrators might be overall faster than using the say opus 4.5 on the bottom for coding. At least we might want to deploy to these guys for simple tasks.
  • adefa
    Benchmarks using DGX Spark on vLLM 0.15.1.dev0+gf17644344 FP8: https://huggingface.co/Qwen/Qwen3-Coder-Next-FP8 Sequential (single request) Prompt Gen Prompt Processing Token Gen Tokens Tokens (tokens/sec) (tokens/sec) ------ ------ ----------------- ----------- 521 49 3,157 44.2 1,033 83 3,917 43.7 2,057 77 3,937 43.6 4,105 77 4,453 43.2 8,201 77 4,710 42.2 Parallel (concurrent requests) pp4096+tg128 (4K context, 128 gen): n t/s -- ---- 1 28.5 2 39.0 4 50.4 8 57.5 16 61.4 32 62.0 pp8192+tg128 (8K context, 128 gen): n t/s -- ---- 1 21.6 2 27.1 4 31.9 8 32.7 16 33.7 32 31.7
  • Tepix
    Using lmstudio-community/Qwen3-Coder-Next-GGUF:Q8_0 I'm getting up to 32 tokens/s on Strix Halo, with room for 128k of context (out of 256k that the model can manage).From very limited testing, it seems to be slightly worse than MiniMax M2.1 Q6 (a model about twice its size). I'm impressed.
  • predkambrij
    17t/s on a laptop with 6GB VRAM and DDR5 system memory. Maximum of 100k context window (then it saturates VRAM). Quite amazing, but tbh I'll still use inference providers, because it's too slow and it's my only machine with "good" specs :) cat docker-compose.yml services: llamacpp: volumes: - llamacpp:/root container_name: llamacpp restart: unless-stopped image: ghcr.io/ggml-org/llama.cpp:server-cuda network_mode: host command: | -hf unsloth/Qwen3-Coder-Next-GGUF:Q4_K_XL --jinja --cpu-moe --n-gpu-layers 999 --ctx-size 102400 --temp 1.0 --top-p 0.95 --min-p 0.01 --top-k 40 --fit on # unsloth/gpt-oss-120b-GGUF:Q2_K deploy: resources: reservations: devices: - driver: nvidia count: all capabilities: [gpu] volumes: llamacpp:
  • 0cf8612b2e1e
    What is the best place to see local model rankings? The benchmarks seem so heavily gamed that I am willing to believe the “objective” rankings are a lie and personal reviews are more meaningful.Are there any clear winners per domain? Code, voice-to-text, text-to-voice, text editing, image generation, text summarization, business-text-generation, music synthesis, whatever.
  • Alifatisk
    As always, the Qwen team is pushing out fantastic contentHope they update the model page soon https://chat.qwen.ai/settings/model
  • cedws
    I kind of lost interest in local models. Then Anthropic started saying I’m not allowed to use my Claude Code subscription with my preferred tools and it reminded me why we need to support open tools and models. I’ve cancelled my CC subscription, I’m not paying to support anticompetitive behaviour.
  • featherless
    I got openclaw to compete Qwen3-Coder-Next vs Minimax M2.1 simultaneously on my Mac Studio 512GB: https://clutch-assistant.github.io/model-comparison-report/
  • macmac_mac
    I just tried qwen 3 tts and it was mind blowingly good, you can even provide directions for the overall tone etc. Which wasn't the case when I used commercial super expensive products like the (now closed after being bought by meta) play.ht .Does anyone see a reason to still use elevenlabs etc. ?
  • StevenNunez
    Not crazy about it. It keeps getting stuck in a loop and filling up the context window (131k, run locally). Kimi's been nice, even if a bit slow.
  • Robdel12
    I really really want local or self hosted models to work. But my experience is they’re not really even close to the closed paid models.Does anyone any experience with these and is this release actually workable in practice?
  • gitpusher
    Pretty cool that they are advertising OpenClaw compatibility. I've tried a few locally-hosted models with OpenClaw and did not get good results – (that tool is a context-monster... the models would get completely overwhelmed them with erroneous / old instructions.)Granted these 80B models are probably optimized for H100/H200 which I do not have. Here's to hoping that OpenClaw compat. survives quantization
  • mmaunder
    These guys are setting up to absolutely own the global south market for AI. Which is in line with the belt and road initiative.
  • blurbleblurble
    So dang exciting! There are a bunch of new interesting small models out lately, by the way, this is just one of them...
  • zokier
    For someone who is very out of the loop with these AI models, can someone explain what I can actually run on my 3080ti (12G)? Is this something like that or is this still too big; is there anything remotely useful runnable with my GPU? I have 64G RAM if that helps (?).
  • ltbarcly3
    Here's a tip: Never name anything new, next, neo, etc. You will have a problem when you try to name the thing after that!
  • zamadatix
    Can anyone help me understand the "Number of Agent Turns" vs "SWE-Bench Pro (%)" figure? I.e. what does the spread of Qwen3-Coder-Next from ~50 to ~280 agent turns represent for a fixed score of 44.3%: that sometimes it takes that spread of agent turns to achieve said fixed score for the given model?
  • ionwake
    will this run on an apple m4 air with 32gb ram?Im currently using qwen 2.5 16b , and it works really well
  • alexellisuk
    Is this going to need 1x or 2x of those RTX PRO 6000s to allow for a decent KV for an active context length of 64-100k?It's one thing running the model without any context, but coding agents build it up close to the max and that slows down generation massively in my experience.
  • storus
    Does Qwen3 allow adjusting context during an LLM call or does the housekeeping need to be done before/after each call but not when a single LLM call with multiple tool calls is in progress?
  • orliesaurus
    how can anyone keep up with all these releases... what's next? Sonnet 5?
  • StevenNunez
    Going to try this over Kimi k2.5 locally. It was nice but just a bit too slow and a resource hog.
  • endymion-light
    Looks great - i'll try to check it out on my gaming PC.On a misc note: What's being used to create the screen recordings? It looks so smooth!
  • ossicones
    What browser use agent are they using here?
  • fudged71
    I'm thrilled. Picked up a used M4 Pro 64GB this morning. Excited to test this out
  • throwaw12
    We are getting there, as a next step please release something to outperform Opus 4.5 and GPT 5.2 in coding tasks
  • dzonga
    the qwen website doesn't work for me in safari :(. had to read the announcement in chrome
  • valcron1000
    Still nothing to compete with GPT-OSS-20B for local image with 16 VRAM.
  • kylehotchkiss
    Is there any online resource tracking local model capability on say... a $2000 64gb memory Mac Mini? I'm getting increasingly excited about the local model space because it offers us a future where we can benefit from LLMs without having to listen to tech CEOs saber rattle about removing America of its jobs so they can get the next fundraising round sorted
  • jtbaker
    any way to run these via ollama yet?
  • syntaxing
    Is Qwen next architecture ironed out in llama cpp?
  • moron4hire
    My IT department is convinced these "ChInEsE cCcP mOdElS" are going to exfiltrate our entire corporate network of its essential fluids and vita.. erh, I mean data. I've tried explaining to them that it's physically impossible for model weights to make network requests on their own. Also, what happened to their MitM-style, extremely intrusive network monitoring that they insisted we absolutely needed?
  • cpill
    I wonder if we could have much smaller models if they train on less languages? i.e. python + yaml + json only or even an single languages with an cluster of models loaded into memory dynamically...?
  • lysace
    Is it censored according to the wishes of the CCP?
  • raphaelmolly8
    [dead]
  • Soerensen
    The agent orchestration point from vessenes is interesting - using faster, smaller models for routine tasks while reserving frontier models for complex reasoning.In practice, I've found the economics work like this:1. Code generation (boilerplate, tests, migrations) - smaller models are fine, and latency matters more than peak capability 2. Architecture decisions, debugging subtle issues - worth the cost of frontier models 3. Refactoring existing code - the model needs to "understand" before changing, so context and reasoning matter moreThe 3B active parameters claim is the key unlock here. If this actually runs well on consumer hardware with reasonable context windows, it becomes the obvious choice for category 1 tasks. The question is whether the SWE-Bench numbers hold up for real-world "agent turn" scenarios where you're doing hundreds of small operations.