Hemmingway 1 — Hardware Requirements & GPU Compatibility
Chat
Hemmingway 1 is a 26.9B-parameter open language model from Altworld. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 16.88 GB of VRAM — see which GPUs and Macs can run it below.
3.8K downloads
577 likesSpecifications
- Publisher
- Altworld
- Parameters
- 26.9B
- Architecture
- Qwen3_5ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-09-20
- License
- CC BY-NC 4.0
Get Started
HuggingFace
How Much VRAM Does Hemmingway 1 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 12.2 GB | 69 GB | 11.43 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 12.5 GB | 69.3 GB | 11.77 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 13.9 GB | 70.7 GB | 13.11 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 14.2 GB | 71.0 GB | 13.45 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 16.9 GB | 73.7 GB | 16.14 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 19.9 GB | 76.7 GB | 19.16 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 22.9 GB | 79.8 GB | 22.19 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 27.6 GB | 84.5 GB | 26.90 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Hemmingway 1?
Q4_K_M · 16.9 GBHemmingway 1 (Q4_K_M) requires 16.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 22+ GB is recommended. Using the full 262K context window can add up to 56.8 GB, bringing total usage to 73.7 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Hemmingway 1?
Q4_K_M · 16.9 GB41 devices with unified memory can run Hemmingway 1, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Hemmingway 1
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Hemmingway 1 need?
Hemmingway 1 requires 16.9 GB of VRAM at Q4_K_M, or 54.5 GB at BF16. Full 262K context adds up to 56.8 GB (73.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 26.9B × 4.8 bits ÷ 8 = 16.1 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 57.6 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M16.9 GBQ4_K_M + full context73.7 GB- Can NVIDIA GeForce RTX 4090 run Hemmingway 1?
Yes, at Q6_K (22.9 GB) or lower. Higher quantizations like Q8_0 (27.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Hemmingway 1?
For Hemmingway 1, Q4_K_M (16.9 GB) offers the best balance of quality and VRAM usage. Q4_K_L (17.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 8.1 GB.
VRAM requirement by quantization
IQ2_XXS8.1 GBQ2_K12.2 GBQ3_K_L14.5 GBQ4_K_M ★16.9 GBQ4_K_L17.2 GBBF1654.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Hemmingway 1 on a Mac?
Hemmingway 1 requires at least 8.1 GB at IQ2_XXS, 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 Hemmingway 1 locally?
Yes — Hemmingway 1 can run locally on consumer hardware. At Q4_K_M quantization it needs 16.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Hemmingway 1?
At Q4_K_M, Hemmingway 1 can reach ~284 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~39 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 ÷ 16.9 × 0.65 = ~308 tok/s
Estimated speed at Q4_K_M (16.9 GB)
~308 tok/s~39 tok/s~308 tok/s~284 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Hemmingway 1?
At Q4_K_M, the download is about 16.14 GB. The full-precision BF16 version is 53.79 GB. The smallest option (IQ2_XXS) is 7.40 GB.
- Which GPUs can run Hemmingway 1?
8 consumer GPUs can run Hemmingway 1 at Q4_K_M (16.9 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Hemmingway 1?
41 devices with unified memory can run Hemmingway 1 at Q4_K_M (16.9 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.