Qwen1.5 110B Chat — Hardware Requirements & GPU Compatibility
Chat
Qwen1.5-110B-Chat is Alibaba Cloud's 111-billion-parameter dense chat model and the largest member of the Qwen1.5 series, which the team describes as a beta version of Qwen2 spanning nine sizes from 0.5B up to this 110B model plus a 14B mixture-of-experts variant. Unlike most other Qwen1.5 sizes, the 110B model uses grouped-query attention, and it was post-trained with supervised fine-tuning and direct preference optimization for improved chat alignment. At 111 billion parameters it needs a multi-GPU workstation to run even when quantized. Context length is 32,768 tokens, one of Qwen1.5's standout features since every size in the family shares a stable 32K window. It is released under the Tongyi Qianwen License Agreement, Alibaba's custom license permitting research and commercial use. It was published in April 2024, a beta step between the original Qwen and Qwen2.
Qwen1.5 110B Chat runs on a 96 GB+ Mac or a workstation GPU
Best local pick → Mac Studio (M3 Ultra, 96GB) · Q4_K_M · 72.4 GB · ~9 tok/s
Macs from 48 GB (IQ2_M · ~11 tok/s)
Other
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen1.5 110B Chat
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/second-state/Qwen1.5-110B-Chat-GGUF:Q4_K_MQ4_K_M · needs ~72.4 GB · 16K context
Download: Qwen1.5-110B-Chat-Q4_K_M-00001-of-00003.gguf67.17 GB + 2 partssecond-state
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 96 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 PRO 6000 (96 GB) (23 GB headroom) · Q4_K_M
- Generation speed
- ~17 tok/s
- generation speed
- Cost per 1M output tokens
- $21.50
- per 1M output tokens
How Much VRAM Does Qwen1.5 110B Chat Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 48.2 GB | 58.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Does not fit: needs 52.9 GB | |
| 49.6 GB | 59.7 GB | 3-bit small — 3-bit small quantization | Does not fit: needs 54.3 GB | |
| 55.2 GB | 65.3 GB | 3-bit medium — 3-bit medium quantization | Does not fit: needs 59.9 GB | |
| 56.6 GB | 66.7 GB | 4-bit · legacy — 4-bit legacy quantization | Does not fit: needs 61.3 GB | |
| 67.7 GB | 77.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Does not fit: needs 72.4 GB | |
| 80.2 GB | 90.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 84.9 GB | |
| 92.7 GB | 102.8 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 97.4 GB | |
| 112.2 GB | 122.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 116.9 GB |
Selected Q4_K_M
4-bit medium quantization72.4GBat 16K context
- Weights
- 66.7 GB
- KV cache
- 5.4 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 48.4 GB more
Or .
Which Hardware Can Run Qwen1.5 110B Chat?
Q4_K_M · 67.7 GBQwen1.5 110B Chat (Q4_K_M) requires 67.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 89+ GB is recommended. Using the full 33K context window can add up to 10.1 GB, bringing total usage to 77.8 GB. No consumer GPU has enough memory. 30 devices with unified memory can run Qwen1.5 110B Chat, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 96GB).
48 GB
48 GB tier →Q4_K_M · best fit IQ2_M (43.2 GB)
2 Mac classes · 1 device family
M5 Max48 GB~11Simulate output on Mac Studio M5 Max (48 GB)M5 Pro48 GB~6Simulate output on Mac Mini M5 Pro (48 GB)Snapdragon X2 Elite Extreme (X2E-96-100)~4Simulate output on Snapdragon X2 Elite Extreme Copilot+ PC96 GB
fits · 23.6 GB free · up to 32K ctx
2 Mac classes
M3 Ultra*96 GB~9Simulate output on Mac Studio (M3 Ultra, 96GB)M3 Max*96 GB~3Simulate output on MacBook Pro 14" M3 Max (96 GB)
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Qwen1.5 110B Chat?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
Here are all 2 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- LMArena Text
LMArena · Oct 2026Arena
Arena1234.2
#134/188 open
- ForecastBench
Epoch AI · Apr 2024Lab-reported
Lab-reported59.5
#19/24 open
Alternatives to Qwen1.5 110B Chat
Qwen family · 28 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| GPT OSS 120BOpenAI | 97.5 | 70.8 GB | —needs > 24 GB | same size |
| Llama 4 Scout 17B 16E InstructMeta | 82.1 | 77 GB | —needs > 24 GB | same size |
| C4ai Command A 03 2025Cohere | 79.8 | 78.7 GB | —needs > 24 GB | same size |
| Leanstral 1.5 119B A6BMistral AI | — | 84 GB | —needs > 24 GB | same size |
| GLM 4.6VZ.ai | — | 66 GB | —needs > 24 GB | same size |
| C4ai Command R Plus 08 2024Cohere | — | 73.8 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- Alibaba
- Family
- Qwen
- Parameters
- 111.2B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2024-04-25
- License
- Other
Frequently Asked Questions
How much VRAM does Qwen1.5 110B Chat need?
Qwen1.5 110B Chat requires 67.7 GB of VRAM at Q4_K_M, or 223.4 GB at BF16. Full 33K context adds up to 10.1 GB (77.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 111.2B × 4.8 bits ÷ 8 = 66.7 GB
KV Cache + Overhead ≈ 1 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 ≈ 11.1 GB (at full 33K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Qwen1.5 110B Chat?
Yes, at IQ2_XXS (31.6 GB) or lower. Higher quantizations like IQ2_XS (34.3 GB) exceed the NVIDIA GeForce RTX 5090's 32 GB.
What's the best quantization for Qwen1.5 110B Chat?
For Qwen1.5 110B Chat, Q4_K_M (67.7 GB) offers the best balance of quality and VRAM usage. Q5_0 (70.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 31.6 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen1.5 110B Chat on a Mac?
Yes — Mac Studio M5 Max (48 GB) and 55 other Macs can run Qwen1.5 110B Chat, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 67.7 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio (M3 Ultra, 96GB).
Can I run Qwen1.5 110B Chat locally?
Yes — Qwen1.5 110B Chat can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen1.5 110B Chat?
At Q4_K_M, Qwen1.5 110B Chat can reach ~71 tok/s on AMD Instinct MI350X. 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 ÷ 67.7 × 0.65 = ~77 tok/s
Estimated speed at Q4_K_M (67.7 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen1.5 110B Chat?
At Q4_K_M, the download is about 66.73 GB. The full-precision BF16 version is 222.42 GB. The smallest option (IQ2_XXS) is 30.58 GB.
Which GPUs can run Qwen1.5 110B Chat?
No single consumer GPU has enough VRAM to run Qwen1.5 110B Chat at Q4_K_M (67.7 GB). Multi-GPU or professional hardware is required.
Which devices can run Qwen1.5 110B Chat?
30 devices with unified memory can run Qwen1.5 110B Chat at Q4_K_M (67.7 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (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.