Baichuan M3 235B — Hardware Requirements & GPU Compatibility
Chat
Baichuan M3 235B is a 235.1B-parameter open language model from baichuan-inc in the Baichuan family. It supports a context window of up to 40,960 tokens. At Q4_K_M it needs about 141.55 GB of VRAM — see which GPUs and Macs can run it below.
Baichuan M3 235B runs on a 192 GB+ Mac or a datacenter GPU
Best local pick → Mac Pro M2 Ultra (192 GB) · Q4_K_M · 142.9 GB · ~23 tok/s
Macs from 128 GB (Q3_K_M · ~26 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Baichuan M3 235B
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
vllm serve baichuan-inc/Baichuan-M3-235B --max-model-len 16384 --tensor-parallel-size 8vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on B200 (192 GB) (49 GB headroom) · Q4_K_M
- Generation speed
- ~129 tok/s
- generation speed
- Cost per 1M output tokens
- $12.86
- per 1M output tokens
How Much VRAM Does Baichuan M3 235B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 100.4 GB | 103.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on Instinct MI250X 128 GB | |
| 115.1 GB | 118.1 GB | 3-bit medium — 3-bit medium quantization | Runs on Instinct MI250X 128 GB | |
| 141.6 GB | 144.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on GH200 Grace Hopper Superchip 144 GB | |
| 168 GB | 171 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on B200 192 GB | |
| 194.4 GB | 197.4 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on Instinct MI325X 256 GB | |
| 235.6 GB | 238.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on Instinct MI325X 256 GB | |
| 470.7 GB | 473.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 7× H100 SXM 80 GB |
Selected Q4_K_M
4-bit medium quantization142.9GBat 16K context
- Weights
- 141.1 GB
- KV cache
- 1.6 GB
- Overhead
- 0.3 GB
Server-class: ~142.9 GB at 16K context · one GH200 Grace Hopper Superchip 144 GB
Or .
Which Hardware Can Run Baichuan M3 235B?
Q4_K_M · 141.6 GBBaichuan M3 235B (Q4_K_M) requires 141.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 185+ GB is recommended. Using the full 41K context window can add up to 3.8 GB, bringing total usage to 145.3 GB. No consumer GPU has enough memory. 4 devices with unified memory can run Baichuan M3 235B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Pro M2 Ultra (192 GB).
128–144 GB
Q4_K_M · best fit Q3_K_M (116.5 GB)
4 GPUs · 2 Mac classes · 1 device family
GH200 Grace Hopper Superchip~117Simulate output on GH200 Grace Hopper SuperchipH200 NVL~116Simulate output on H200 NVLH200 SXM~116Simulate output on H200 SXMM2 Ultra*128 GB~26Simulate output on Mac Pro M2 Ultra (128 GB)M5 Max128 GB~23Simulate output on Mac Studio M5 Max (128 GB)GB10~15Simulate output on NVIDIA DGX Spark192+ GB
fits · 49.1 GB free · up to 40K ctx
6 GPUs · 1 Mac class · 2 device families
B200~129Simulate output on B200B300~129Simulate output on B300Instinct MI350X~46Simulate output on Instinct MI350XM3 Ultra*256–512 GB~24Simulate output on Mac Studio (M3 Ultra, 256GB)8x H100 SXM5~168Simulate output on NVIDIA DGX H1008x A100 SXM4~156Simulate output on NVIDIA DGX A100 640GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 96 GB: too small for this model (needs ≥ 101.8 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Alternatives to Baichuan M3 235B
Baichuan family · 6 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniMax M2.7MiniMax | 107.4 | 139.6 GB | —needs > 24 GB | same size |
| Command A Plus 05 2026 BF16Cohere | — | 132.1 GB | —needs > 24 GB | same size |
| Qwen3 VL 235B A22B InstructAlibaba | — | 143.3 GB | —needs > 24 GB | same size |
| DeepSeek V2.5 1210DeepSeek | — | 142.9 GB | —needs > 24 GB | same size |
| Laguna M.1poolside | — | 138.1 GB | —needs > 24 GB | same size |
| Llama 3 1 Nemotron Ultra 253B V1NVIDIA | — | 564.2 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- baichuan-inc
- Family
- Baichuan
- Parameters
- 235.1B
- Active parameters
- 22.2B per token
- Architecture
- Qwen3MoeForCausalLM
- Context Length
- 40,960 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-01-13
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Baichuan M3 235B need?
Baichuan M3 235B requires 141.6 GB of VRAM at Q4_K_M, or 470.7 GB at BF16. Full 41K context adds up to 3.8 GB (145.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 235.1B × 4.8 bits ÷ 8 = 141.1 GB
KV Cache + Overhead ≈ 0.5 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 ≈ 4.2 GB (at full 41K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Baichuan M3 235B?
No — Baichuan M3 235B requires at least 100.4 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for Baichuan M3 235B?
For Baichuan M3 235B, Q4_K_M (141.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (168 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 100.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Baichuan M3 235B on a Mac?
Yes — Mac Pro M2 Ultra (128 GB) and 14 other Macs can run Baichuan M3 235B, the smallest at Q3_K_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 141.6 GB of usable unified memory (RAM minus macOS overhead), from Mac Pro M2 Ultra (192 GB).
Can I run Baichuan M3 235B locally?
Yes — Baichuan M3 235B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Baichuan M3 235B?
At Q4_K_M, Baichuan M3 235B can reach ~46 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 13.4 GB active ÷ (8000 × 0.65) = 2.57 ms, plus 94 layers × 0.055 ms = 5.17 ms, so 1000 ÷ 7.74 ms = ~129 tok/s
Estimated speed at Q4_K_M (141.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Baichuan M3 235B?
At Q4_K_M, the download is about 141.06 GB. The full-precision BF16 version is 470.19 GB. The smallest option (Q2_K) is 99.91 GB.
Which GPUs can run Baichuan M3 235B?
No single consumer GPU has enough VRAM to run Baichuan M3 235B at Q4_K_M (141.6 GB). Multi-GPU or professional hardware is required.
Which devices can run Baichuan M3 235B?
4 devices with unified memory can run Baichuan M3 235B at Q4_K_M (141.6 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.