Qwen 27B vs 35B A3B for coding
Coding quality under a 64 GB planning ceiling
Facts from the reviewed catalog
| Specification | Qwen3.8 27B | Qwen3.5 35B A3B |
|---|---|---|
| Task | Text & chat | Text & chat |
| Parameters | 27B | 35B · 3B active |
| License | Apache 2.0 | Apache 2.0 |
| Commercial use | Allowedlicense text | Allowedlicense text |
| Quality · LiveBench 2026-06-25 | 75.3overall · 0–100 · source | No score in LiveBench 2026-06-25 · source |
| Memory | Q4 planning estimate (~21 GB of weights before the machine's reserve) | Q4 planning estimate (~27 GB of weights before the machine's reserve) |
| Checkpoint | official card | official card |
Only Qwen3.8 27B has a result in LiveBench 2026-06-25 (75.3); Qwen3.5 35B A3B has none, so the two are not ranked from this source and no score is inferred for it. Questions with verifiable answers, released monthly; a score belongs to its release. Scale: overall score, 0–100, higher is better.
Memory on three machines
Each machine's own reserve is added (graphics cards 2 GB; unified and system memory 25%, 2 to 8 GB). Planning estimates, not measured runs.
| Machine | Qwen3.8 27B | Qwen3.5 35B A3B |
|---|---|---|
| RTX 4090 · 24 GB VRAM | ~23 GBFast memory holds it | ~29 GBIn memory, outside the fast part · offload to PC RAM (32 GB assumed) |
| RTX 5090 · 32 GB VRAM | ~23 GBFast memory holds it | ~29 GBFast memory holds it |
| Mac mini M5 Pro · 64 GB unified | ~29 GBFast memory holds it | ~35 GBFast memory holds it |
Qwen3.8 27B: Q4 planning estimate (~21 GB of weights before the machine's reserve). Qwen3.5 35B A3B: Q4 planning estimate (~27 GB of weights before the machine's reserve). Formulas
Everything that runs on each machine: RTX 4090 · 24 GB VRAM · RTX 5090 · 32 GB VRAM · Mac mini M5 Pro · 64 GB unified
Which to choose
The 27B is dense; the 35B A3B is a mixture of experts that activates about 3 billion parameters per token. The mixture of experts needs more memory, because all 35 billion weights must be loaded, but each token does less work, so it tends to generate faster once it fits. The dense 27B needs less memory. Both are Apache 2.0 and take text, image and video. Neither score here is a coding benchmark: check the publisher's coding results below and test on your own repository.
Files and run commands
The default file of the most downloaded collected source, or the commands each card documents. Not run by this site.
Qwen3.8 27B
unsloth/Qwen3.8-27B-GGUF · Qwen3.8-27B-UD-Q4_K_M.gguf · UD-Q4_K_M · 16.5 GB · unsloth
ollama run hf.co/unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_Mllama-server -hf unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_Mlms get https://huggingface.co/unsloth/Qwen3.8-27B-GGUF- mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac
Qwen3.5 35B A3B
unsloth/Qwen3.5-35B-A3B-GGUF · Qwen3.5-35B-A3B-Q4_K_M.gguf · Q4_K_M · 22 GB · unsloth
ollama run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_Mllama-server -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_Mlms get https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF- mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac
Numbers each publisher reports
Each card's own results with its own settings. Publishers choose different tests and settings, so these values are never compared across publishers here.
Qwen3.8 27B · reported by Alibaba
- Agentic terminal coding Terminal Bench 2.1 (Terminus)
- 73.0Text Performance
- Agentic coding SWE-bench Pro
- 61.7Text Performance
- Repo-level code generation NL2Repo-Bench
- 42.3Text Performance
- Agentic coding DeepSWE 1.1
- 42.2Text Performance
- Software engineering QwenSWEBench
- 79.0Text Performance
- Long-horizon office work CoWorkBench
- 70.7Text Performance
- Professional job tasks JobBench
- 33.4Text Performance
- Instruction following IFBench
- 79.5Text Performance
Every reported result
- Scientific reasoning GPQA Diamond
- 89.2Text Performance
- Multidisciplinary reasoning HLE
- 30.8Text Performance
- Competitive coding LiveCodeBench v6
- 90.3Text Performance
- Computer use OSWorld-Verified
- 84.3VL Performance
- Browser use WebArena-Verified
- 64.8VL Performance
- Mobile use AndroidWorld
- 81.9VL Performance
- Application recreation RecreationBench
- 47.1VL Performance
- Multimodal software engineering SWE-MM
- 38.6VL Performance
- Visual web development Vision2Web
- 62.9VL Performance
- Document intelligence OmniDocBench 1.5
- 91.1VL Performance
- Real-world perception RealWorldQA
- 85.9VL Performance
- Embodied intelligence ERQA
- 65.5VL Performance
Values as printed on the card, with the publisher's own settings (card section: Benchmark Results › Text Performance; Benchmark Results › VL Performance); column “Qwen3.8-27B”. Not comparable across publishers and not used in any ranking. Model card
Qwen3.5 35B A3B · reported by Alibaba
- MMLU-Pro
- 85.3Language
- MMLU-Redux
- 93.3Language
- C-Eval
- 90.2Language
- SuperGPQA
- 63.4Language
- IFEval
- 91.9Language
- IFBench
- 70.2Language
- MultiChallenge
- 60.0Language
- AA-LCR
- 58.5Language
Every reported result
- LongBench v2
- 59.0Language
- HLE w/ CoT
- 22.4Language
- GPQA Diamond
- 84.2Language
- HMMT Feb 25
- 89.0Language
- HMMT Nov 25
- 89.2Language
- SWE-bench Verified
- 69.2Language
- Terminal Bench 2
- 40.5Language
- LiveCodeBench v6
- 74.6Language
- CodeForces
- 2,028Language
- OJBench
- 36.0Language
- FullStackBench en
- 58.1Language
- FullStackBench zh
- 55.0Language
- BFCL-V4
- 67.3Language
- TAU2-Bench
- 81.2Language
- VITA-Bench
- 31.9Language
- DeepPlanning
- 22.8Language
- HLE w/ tool
- 47.4Language
- Browsecomp
- 61.0Language
- Browsecomp-zh
- 69.5Language
- WideSearch
- 57.1Language
- Seal-0
- 41.4Language
- MMMLU
- 85.2Language
- MMLU-ProX
- 81.0Language
- NOVA-63
- 57.1Language
- INCLUDE
- 79.7Language
- Global PIQA
- 86.6Language
- PolyMATH
- 64.4Language
- WMT24++
- 76.3Language
- MAXIFE
- 86.6Language
- MMMU
- 81.4Vision Language
- MMMU-Pro
- 75.1Vision Language
- MathVision
- 83.9Vision Language
- Mathvista (mini)
- 86.2Vision Language
- DynaMath
- 85.0Vision Language
- ZEROBench
- 8Vision Language
- ZEROBench_sub
- 34.1Vision Language
- VlmsAreBlind
- 97.0Vision Language
- RealWorldQA
- 84.1Vision Language
- MMStar
- 81.9Vision Language
- MMBench EN-DEV-v1.1
- 91.5Vision Language
- SimpleVQA
- 58.3Vision Language
- HallusionBench
- 67.9Vision Language
- OmniDocBench1.5
- 89.3Vision Language
- CharXiv (RQ)
- 77.5Vision Language
- MMLongBench-Doc
- 59.5Vision Language
- CC-OCR
- 80.7Vision Language
- AI2D_TEST
- 92.6Vision Language
- OCRBench
- 91.0Vision Language
- ERQA
- 64.8Vision Language
- CountBench
- 97.8Vision Language
- RefCOCO (avg)
- 89.2Vision Language
- ODInW13
- 42.6Vision Language
- EmbSpatialBench
- 83.1Vision Language
- RefSpatialBench
- 63.5Vision Language
- LingoQA
- 79.2Vision Language
- Hypersim
- 13.1Vision Language
- SUNRGBD
- 33.4Vision Language
- Nuscene
- 14.6Vision Language
- VideoMME (w sub.)
- 86.6Vision Language
- VideoMME (w/o sub.)
- 82.5Vision Language
- VideoMMMU
- 80.4Vision Language
- MLVU
- 85.6Vision Language
- MVBench
- 74.8Vision Language
- LVBench
- 71.4Vision Language
- MMVU
- 72.3Vision Language
- ScreenSpot Pro
- 68.6Vision Language
- OSWorld-Verified
- 54.5Vision Language
- AndroidWorld
- 71.1Vision Language
- SLAKE
- 78.7Vision Language
- PMC-VQA
- 62.0Vision Language
- MedXpertQA-MM
- 61.4Vision Language
Values as printed on the card, with the publisher's own settings (card section: Benchmark Results › Language; Benchmark Results › Vision Language); column “Qwen3.5-35B-A3B”. Not comparable across publishers and not used in any ranking. Model card
Limits and dates
The published quality benchmark does not test a local quantized build. Memory estimates are not speed measurements or guaranteed hardware fits. Repository size, when available, is not VRAM. Formulas
Page updated · Catalog reviewed · LiveBench 2026-06-25, collected