OmniCoder 9B MLX Mxfp8 — Hardware Requirements & GPU Compatibility
ChatCodeFunctions
191 downloads
2 likesSpecifications
- Publisher
- arthurcollet
- Parameters
- 9.0B
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-03-13
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does OmniCoder 9B MLX Mxfp8 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 4.4 GB | 38.5 GB | 3.81 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 4.5 GB | 38.6 GB | 3.92 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 4.9 GB | 39.0 GB | 4.36 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 5.0 GB | 39.1 GB | 4.48 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 5.9 GB | 40.0 GB | 5.37 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 7.0 GB | 41.0 GB | 6.38 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 8.0 GB | 42.0 GB | 7.39 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 9.5 GB | 43.6 GB | 8.95 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run OmniCoder 9B MLX Mxfp8?
Q4_K_M · 5.9 GBOmniCoder 9B MLX Mxfp8 (Q4_K_M) requires 5.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 262K context window can add up to 34.1 GB, bringing total usage to 40.0 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run OmniCoder 9B MLX Mxfp8?
Q4_K_M · 5.9 GB33 devices with unified memory can run OmniCoder 9B MLX Mxfp8, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does OmniCoder 9B MLX Mxfp8 need?
OmniCoder 9B MLX Mxfp8 requires 5.9 GB of VRAM at Q4_K_M, or 9.5 GB at Q8_0. Full 262K context adds up to 34.1 GB (40.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 9.0B × 4.8 bits ÷ 8 = 5.4 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 34.6 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M5.9 GBQ4_K_M + full context40.0 GB- What's the best quantization for OmniCoder 9B MLX Mxfp8?
For OmniCoder 9B MLX Mxfp8, Q4_K_M (5.9 GB) offers the best balance of quality and VRAM usage. Q4_K_L (6.0 GB) provides better quality if you have the VRAM. The smallest option is IQ2_S at 3.4 GB.
VRAM requirement by quantization
IQ2_S3.4 GB~59%Q3_K_S4.5 GB~77%IQ4_XS5.4 GB~87%Q4_K_M ★5.9 GB~89%Q4_K_L6.0 GB~90%Q8_09.5 GB~99%★ Recommended — best balance of quality and VRAM usage.
- Can I run OmniCoder 9B MLX Mxfp8 on a Mac?
OmniCoder 9B MLX Mxfp8 requires at least 3.4 GB at IQ2_S, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run OmniCoder 9B MLX Mxfp8 locally?
Yes — OmniCoder 9B MLX Mxfp8 can run locally on consumer hardware. At Q4_K_M quantization it needs 5.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is OmniCoder 9B MLX Mxfp8?
At Q4_K_M, OmniCoder 9B MLX Mxfp8 can reach ~491 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~110 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 5.9 × 0.55 = ~491 tok/s
Estimated speed at Q4_K_M (5.9 GB)
AMD Instinct MI300X~491 tok/sNVIDIA GeForce RTX 4090~110 tok/sNVIDIA H100 SXM~367 tok/sAMD Instinct MI250X~303 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of OmniCoder 9B MLX Mxfp8?
At Q4_K_M, the download is about 5.37 GB. The full-precision Q8_0 version is 8.95 GB. The smallest option (IQ2_S) is 2.80 GB.
- Which GPUs can run OmniCoder 9B MLX Mxfp8?
35 consumer GPUs can run OmniCoder 9B MLX Mxfp8 at Q4_K_M (5.9 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 28 GPUs have plenty of headroom for comfortable inference.
- Which devices can run OmniCoder 9B MLX Mxfp8?
33 devices with unified memory can run OmniCoder 9B MLX Mxfp8 at Q4_K_M (5.9 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.