Qwen3.5 27B — Hardware Requirements & GPU Compatibility
VisionFunctions
Qwen3.5 27B is a 27.8-billion-parameter dense model from Alibaba's Qwen team, built for both text and image input using the same hybrid linear/full-attention architecture as the rest of the Qwen3.5 family. As a vision-capable model it can describe and reason about images alongside prompts, suiting multimodal chat and document tasks. At this size, local inference calls for quantization and a single high-end 24GB-plus consumer or workstation GPU rather than budget hardware. It supports a 262K token context window for long documents and multi-turn conversations, and is released under the Apache 2.0 license for unrestricted commercial and research use. Published in late February 2026, it sits alongside a separate small-model tier (0.8B–9B) in the same family, giving developers a mid-sized, single-GPU-friendly dense option.
Runs well on a 24 GB GPU
Runs from 12 GB (IQ3_XXS · 16K)Best on 24 GB (Q4_K_M · ~38 tok/s · 64K)Macs from 16 GB (Q2_K_S · ~12 tok/s)
Score 103.8#48 of 106 open#7 of 36 that fit 24 GBApache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
103.8
- 90% range 97.9–109.6
- #48 of 106 open models
- #7 of 36 that fit 24 GB
Run Qwen3.5 27B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/unsloth/Qwen3.5-27B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 6.1 GB free · 16K context
Download: Qwen3.5-27B-Q4_K_M.gguf16.74 GBunsloth
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3090 (24 GB) (6 GB headroom) · Q4_K_M
- Generation speed
- ~35 tok/s
- generation speed
- Cost per 1M output tokens
- $1.35
- per 1M output tokens
How Much VRAM Does Qwen3.5 27B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 12.6 GB | 13.9 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~52 tok/s | |
| 12.9 GB | 14.2 GB | 3-bit small — 3-bit small quantization | Fits: 128K context · ~51 tok/s | |
| 14.3 GB | 15.6 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~46 tok/s | |
| 14.6 GB | 16 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 128K context · ~45 tok/s | |
| 17.4 GB | 18.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 64K context · ~38 tok/s | |
| 20.5 GB | 21.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 64K context · ~32 tok/s | |
| 23.7 GB | 25 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 8K context · ~28 tok/s | |
| 28.5 GB | 29.9 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 29 GB |
Selected Q4_K_M
4-bit medium quantization17.9GBat 16K context
- Weights
- 16.7 GB
- KV cache
- 0.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 6.1 GB free · ~38 tok/s
≥50 tok/s needs ≥1.34 TB/s · RTX 5090 ~67
Which Hardware Can Run Qwen3.5 27B?
Q4_K_M · 17.4 GBQwen3.5 27B (Q4_K_M) requires 17.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 23+ GB is recommended. Using the full 262K context window can add up to 13.9 GB, bringing total usage to 31.3 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Qwen3.5 27B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 2.1 GB free · up to 32K ctx
1 GPU
RX 7900 XT~28Simulate output on RX 7900 XT32–40 GB
fits · 14.1 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~67Simulate output on RTX 5090M5 Max36 GB~19Simulate output on Mac Studio M5 Max (36 GB)M532 GB~6Simulate output on MacBook Air 13" M5 (32 GB)Orin~8Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~5Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Qwen3.5 27B?
The llmrun Score merges 6 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the 24 GB tier
- Qwen3.5 27B
- Other models
- Best Score for its VRAM
#7 of 36 that fit 24 GB
Each dot is a model at the best quant that fits a 24 GB GPU. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.
Full 24 GB ranking →Benchmarks
The 6 boards that weigh most in the llmrun Score, of 8 with a result for this model; badges show who ran the test.
- LMArena Text
LMArena · Oct 2026Arena
Arena1408.8
#45/188 open
- LMArena WebDev
LMArena · Oct 2026Arena
Arena1358.3
#39/55 open
- MMLU-Pro
TIGER-LabIndependent
Independent86.1%
#5/146 open
- WeirdML
Epoch AI · Feb 2026Independent
Independent39.5%
#24/47 open
- ALE-Bench
Epoch AI · Feb 2026Lab-reported
Lab-reported349.4
#41/48 open
- DTBench
Epoch AI · Feb 2026Lab-reported
Lab-reported82.4%
#21/70 open
In the 24 GB class
36 models fit 24 GBSame Score, only models that fit 24 GB at their best quant: the ranking a 24 GB owner actually chooses from.
- #1
Qwen3.8 27BAlibaba
122.0
~38 tok/s · 17.9 GB
- #2
Qwen3.6 27BAlibaba
111.2
~38 tok/s · 17.9 GB
- #3
Qwen3.6 35B A3BAlibaba
106.8
~151 tok/s · 22.0 GB
- #4
Gemma 4 31B ITGoogle
106.7
~32 tok/s · 21.7 GB
- #5
Gemma 4 26B A4B ITGoogle
105.8
~171 tok/s · 16.5 GB
- #6
Qwen3.5 35B A3BAlibaba
105.8
~151 tok/s · 22.0 GB
Alternatives to Qwen3.5 27B
Qwen 3.5 family · 34 models →Official models with an llmrun Score, each answering one question; numbers are at the best quant that fits a 24 GB GPU.
Best alternative at this size
Qwen3.8 27B
Alibaba
- 18.2 higher Score
Score 122.0 · 17.9 GB · ~38 tok/s
Much faster, similar quality
Qwen3.6 35B A3B
Alibaba
- 3 higher Score
- 4.2 GB more VRAM
- 113 tok/s faster
Score 106.8 · 22 GB · ~151 tok/s
Fits in less VRAM
GPT OSS 20B
OpenAI
- 7.4 lower Score
- 4.7 GB less VRAM
- 152 tok/s faster
Score 96.4 · 13.1 GB · ~190 tok/s
Other vendor
Gemma 4 31B IT
Google
- 2.9 higher Score
- 3.8 GB more VRAM
- 5 tok/s slower
Score 106.7 · 21.7 GB · ~32 tok/s
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | similar score |
| Gemma 4 26B A4B ITGoogle | 105.8 | 16.5 GB | ~171 | similar score |
| Qwen3.5 35B A3BAlibaba | 105.8 | 22 GB | ~151 | similar score |
| Seed OSS 36B InstructByteDance-Seed | 102.5 | 22.8 GB | ~31 | similar score |
| Qwen3 30B A3B Thinking 2507Alibaba | 100.7 | 19.4 GB | ~173 | similar score |
| Qwen3 32BAlibaba | 98.6 | 22.6 GB | ~32 | similar score |
| Qwen3 14BAlibaba | 98.0 | 11.9 GB | ~69 | similar score |
| DeepSeek R1 Distill Qwen 32BDeepSeek | 97.2 | 23 GB | ~34 | similar score |
| QwQ 32BAlibaba | 96.2 | 23 GB | ~34 | similar score |
| Qwen3 8BAlibaba | 93.9 | 7.6 GB | ~119 | similar score |
Specifications
- Publisher
- Alibaba
- Family
- Qwen 3.5
- Parameters
- 27.8B
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-02-24
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3.5 27B need?
Qwen3.5 27B requires 17.4 GB of VRAM at Q4_K_M, or 56.3 GB at BF16. Full 262K context adds up to 13.9 GB (31.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 27.8B × 4.8 bits ÷ 8 = 16.7 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 14.6 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Qwen3.5 27B?
Yes, at Q6_K (23.7 GB) or lower. Higher quantizations like Q8_0 (28.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Qwen3.5 27B?
For Qwen3.5 27B, Q4_K_M (17.4 GB) offers the best balance of quality and VRAM usage. Q4_K_L (17.8 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 8.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3.5 27B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Qwen3.5 27B, the smallest at Q2_K_S. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 17.4 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Qwen3.5 27B locally?
Yes — Qwen3.5 27B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3.5 27B?
At Q4_K_M, Qwen3.5 27B can reach ~276 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~38 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 17.4 × 0.65 = ~299 tok/s
Estimated speed at Q4_K_M (17.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen3.5 27B?
At Q4_K_M, the download is about 16.67 GB. The full-precision BF16 version is 55.56 GB. The smallest option (IQ2_XXS) is 7.64 GB.
Which GPUs can run Qwen3.5 27B?
8 consumer GPUs can run Qwen3.5 27B at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Qwen3.5 27B?
122 devices with unified memory can run Qwen3.5 27B at Q4_K_M (17.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.